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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric revision identifiers (the “rev” values) in CouchDB‐style JSON responses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     disrupting
    -0.08
     organizational
    -0.07
    Fortunately
    -0.07
     struggle
    -0.06
     digits
    -0.06
     think
    -0.06
    icro
    -0.06
    _value
    -0.06
     ihren
    -0.06
     limits
    -0.06
    POSITIVE LOGITS
     dlouho
    0.06
    mark
    0.06
    .tagName
    0.06
     �
    0.06
     pelic
    0.06
    xad
    0.06
    iki
    0.06
    izm
    0.06
    egin
    0.06
    Patrick
    0.06
    Act Density 0.016%

    No Known Activations