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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avn
    -0.07
     been
    -0.07
    ۰۰
    -0.07
     уник
    -0.06
    nier
    -0.06
     mirrors
    -0.06
    то
    -0.06
    Dal
    -0.06
     predicting
    -0.06
    classed
    -0.06
    POSITIVE LOGITS
     Viewer
    0.07
    ()
    0.07
    VersionUID
    0.07
    联合
    0.06
    AUTHORIZED
    0.06
    :def
    0.06
     [_
    0.06
    ẩn
    0.06
     уход
    0.06
     فوق
    0.06
    Act Density 0.000%

    No Known Activations