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

    Neuronpedia

    INDEX
    Explanations

    references to detailed explanations and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    full review or detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndProject
    -0.81
    SharedCtor
    -0.77
    saraba
    -0.75
    новниш
    -0.73
     GenerationType
    -0.68
    pexpr
    -0.68
    <unused28>
    -0.67
    <unused39>
    -0.67
    <unused1>
    -0.67
    [@BOS@]
    -0.67
    POSITIVE LOGITS
     fuller
    0.39
     full
    0.34
     detailed
    0.32
     fulness
    0.32
     полно
    0.31
    Full
    0.31
    Detailed
    0.29
    full
    0.29
    详细
    0.28
     detal
    0.28
    Act Density 0.069%

    No Known Activations