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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical or system-based instructions

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

    language or punctuation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    appcompat
    -0.42
     fæ
    -0.38
     Aussicht
    -0.34
     Busch
    -0.33
     irré
    -0.33
     McCann
    -0.33
    هما
    -0.31
     discretion
    -0.31
    FE
    -0.31
    شان
    -0.30
    POSITIVE LOGITS
     Numerade
    0.84
    hyrchwyd
    0.67
     Италијани
    0.65
    parsedMessage
    0.61
     surla
    0.58
    astéroïdes
    0.56
    Manbalar
    0.56
    aarrggbb
    0.54
    Hauptartikel
    0.54
     Combien
    0.53
    Act Density 0.009%

    No Known Activations