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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and thematic elements associated with darkness and suspense

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

    before parentheses or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    book titles and story names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.44
    opor
    -0.40
    imach
    -0.39
    atuur
    -0.39
    astas
    -0.38
    ogos
    -0.38
    ofia
    -0.38
     gió
    -0.37
     kasarigan
    -0.37
     magnify
    -0.37
    POSITIVE LOGITS
     оригіналу
    0.49
    SequentialGroup
    0.48
    RTEE
    0.47
     wikipagina
    0.47
    ThemeOverlay
    0.45
     חיצוניים
    0.43
    ToBounds
    0.43
    permitAll
    0.43
    elemField
    0.42
     kaynağından
    0.42
    Act Density 0.351%

    No Known Activations