Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    a an

    np_max-act · gemini-2.0-flash

    technical jargon related to data storage and processing systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively activates on common grammatical function words—articles, conjunctions, determiners, and quantifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     alanında
    -0.07
     gaps
    -0.07
     linguistic
    -0.07
     Gonzalez
    -0.07
    loss
    -0.06
    -errors
    -0.06
    ρή
    -0.06
    .sys
    -0.06
    りに
    -0.06
     neglect
    -0.06
    POSITIVE LOGITS
    ................................
    0.07
     vyb
    0.07
    ................................................................
    0.06
    {};↵
    0.06
    KT
    0.06
     ((*
    0.06
     ParameterDirection
    0.06
     Cover
    0.06
    {l
    0.06
    *****↵
    0.06
    Act Density 0.039%

    No Known Activations