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
    _locals
    -0.07
     lose
    -0.07
     ар
    -0.07
    bash
    -0.06
    .VarChar
    -0.06
    _IW
    -0.06
    왔다
    -0.06
     заход
    -0.06
     předpis
    -0.06
     floated
    -0.06
    POSITIVE LOGITS
     منابع
    0.07
    agem
    0.07
    uni
    0.07
    ім
    0.07
     À
    0.06
    /flutter
    0.06
     기능
    0.06
    56
    0.06
     exposure
    0.06
    _FMT
    0.06
    Act Density 0.000%

    No Known Activations