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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lambda
    -0.08
    LAT
    -0.07
    Cal
    -0.06
     creeping
    -0.06
     ngày
    -0.06
    'E
    -0.06
    Delay
    -0.06
    Markup
    -0.06
    OLE
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    638
    0.06
    еристи
    0.06
    Electric
    0.06
    ığı
    0.06
    適用
    0.06
    _not
    0.06
     kills
    0.06
    işim
    0.06
    ')"↵
    0.06
     const
    0.06
    Act Density 0.013%

    No Known Activations