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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avalanche
    -0.07
    .retry
    -0.07
    IRTUAL
    -0.07
    regor
    -0.06
    agas
    -0.06
     hurricanes
    -0.06
    instead
    -0.06
    рон
    -0.06
    ppelin
    -0.06
     opr
    -0.06
    POSITIVE LOGITS
     discour
    0.07
     dov
    0.06
    .optString
    0.06
    ');↵↵↵
    0.06
     ヴ
    0.06
    !(:
    0.06
     Lag
    0.06
    (\'
    0.06
    )e
    0.06
    ',$
    0.06
    Act Density 0.035%

    No Known Activations