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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron activates on large numeric expressions—specifically multi-digit numbers using comma separators (e.g. “3,756,” “4,444,” “51,440”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Overrides
    -0.06
    966
    -0.06
    obo
    -0.06
     Profession
    -0.06
    asher
    -0.06
     letz
    -0.06
    banana
    -0.06
     unary
    -0.06
    unkt
    -0.06
    ulum
    -0.06
    POSITIVE LOGITS
     ­
    0.08
     EXEMPLARY
    0.07
     Eins
    0.07
    (Temp
    0.07
    _picture
    0.06
    .keySet
    0.06
     v
    0.06
    bild
    0.06
     baktı
    0.06
     trailing
    0.06
    Act Density 0.018%

    No Known Activations