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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical symbols

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

    Tokens preceding integers or decimals

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gotcha
    -0.48
    IPPING
    -0.43
    getitem
    -0.40
     so
    -0.40
    inge
    -0.39
    ajú
    -0.38
    Context
    -0.38
    acional
    -0.38
    so
    -0.38
    or
    -0.38
    POSITIVE LOGITS
    LookAnd
    1.03
    GEBURTSDATUM
    0.97
     المعيارى
    0.93
     صوتيه
    0.84
    ंदीखरीदारी
    0.82
     onCreateView
    0.81
     متعلقه
    0.81
    ContentAsync
    0.81
    UserScript
    0.81
    MigrationBuilder
    0.81
    Act Density 0.445%

    No Known Activations