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

    Neuronpedia

    INDEX
    Explanations

    code-related declarations and dependencies

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

    code imports and data derivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.50
    buttonBar
    -0.45
    gdala
    -0.41
    pagation
    -0.40
     مشين
    -0.40
    новниш
    -0.39
     nonatomic
    -0.38
     الحره
    -0.38
    VertexAttrib
    -0.37
    اف
    -0.37
    POSITIVE LOGITS
    setVerticalGroup
    0.56
     rainha
    0.44
     étrangère
    0.41
     caminh
    0.41
    جغرافيا
    0.41
     esquerda
    0.40
     diretamente
    0.39
     FixedUpdate
    0.39
     simplesmente
    0.38
    Коро
    0.38
    Act Density 0.001%

    No Known Activations