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

    Neuronpedia

    INDEX
    Explanations

    patterns related to classification or categorization

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

    Characters often found in code or equations

    np_acts-logits-general · gemini-2.0-flash

    testing reset or specific values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nime
    -0.49
    確認ください
    -0.44
    仰
    -0.44
     prosz
    -0.44
    getD
    -0.42
    ütte
    -0.41
     pob
    -0.41
    ütten
    -0.40
     Nó
    -0.39
    gena
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    1.17
    principalColumn
    1.04
    TagMode
    0.93
     ویکی‌پدیا
    0.90
    󠁮
    0.86
    featureID
    0.83
     pinulongan
    0.82
    Rptr
    0.80
    сылкі
    0.79
    ReusableCell
    0.77
    Act Density 0.348%

    No Known Activations