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

    Neuronpedia

    INDEX
    Explanations

    Requests to stop behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     APR
    -0.07
    .Movie
    -0.07
     adb
    -0.06
     Photographer
    -0.06
     نزد
    -0.06
    (Log
    -0.06
     Комп
    -0.06
     Exp
    -0.06
    >User
    -0.06
    $IFn
    -0.06
    POSITIVE LOGITS
    χε
    0.07
     parameter
    0.07
    (training
    0.07
    ätt
    0.07
    enger
    0.06
    Floating
    0.06
     hoàng
    0.06
     defaultCenter
    0.06
    报告
    0.06
    border
    0.06
    Act Density 0.022%

    No Known Activations