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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PATCH
    -0.07
     simulated
    -0.07
     iy
    -0.07
    能源
    -0.07
     loft
    -0.07
    DataFrame
    -0.07
     gö
    -0.06
    :self
    -0.06
    .byId
    -0.06
    ipar
    -0.06
    POSITIVE LOGITS
    .AutoScaleMode
    0.07
     Bind
    0.06
     Πρω
    0.06
    -too
    0.06
     Early
    0.06
    iste
    0.06
     unlock
    0.06
    _rr
    0.06
    ض
    0.06
    -lo
    0.06
    Act Density 0.003%

    No Known Activations