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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    This neuron activates on capitalized proper nouns (e.g. names of people, brands, and other named entities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Q
    -0.07
     پیچ
    -0.06
    .prop
    -0.06
     Crack
    -0.06
    ynth
    -0.06
    ame
    -0.06
    Triangles
    -0.06
     recreational
    -0.06
     affid
    -0.06
     Needle
    -0.06
    POSITIVE LOGITS
     firmy
    0.07
    IFI
    0.07
    شر
    0.07
    ^[
    0.06
    ,out
    0.06
     gouver
    0.06
    身
    0.06
     dared
    0.06
     STREET
    0.06
     assez
    0.06
    Act Density 0.158%

    No Known Activations