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

    Neuronpedia

    INDEX
    Explanations

    competitions and events

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—especially floating‐point or decimal values—in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ushing
    -0.06
    ено
    -0.06
     Mr
    -0.06
    けて
    -0.06
    Marcus
    -0.06
    .Setter
    -0.06
    .filters
    -0.06
    одерж
    -0.06
     Plates
    -0.06
     onLoad
    -0.06
    POSITIVE LOGITS
    (UInt
    0.07
    薦
    0.07
    怀
    0.06
     Saved
    0.06
    SO
    0.06
    ям
    0.06
     rumored
    0.06
     possível
    0.06
    youtube
    0.06
    _CE
    0.06
    Act Density 0.209%

    No Known Activations