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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing real‐valued quantities (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Woman
    -0.07
     aspects
    -0.07
     fs
    -0.06
    _LIST
    -0.06
    Hat
    -0.06
     stigma
    -0.06
     scenarios
    -0.06
    .lp
    -0.06
    रण
    -0.06
     Array
    -0.06
    POSITIVE LOGITS
    \Models
    0.07
     están
    0.06
     meisten
    0.06
     velmi
    0.06
     masih
    0.06
     перен
    0.06
    atorial
    0.06
    .terminate
    0.06
     mid
    0.06
    acyj
    0.06
    Act Density 0.145%

    No Known Activations