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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Officers
    -0.07
    ियत
    -0.07
    ests
    -0.07
     been
    -0.06
    墙
    -0.06
    oit
    -0.06
    pie
    -0.06
     HOUR
    -0.06
     favour
    -0.06
     закуп
    -0.06
    POSITIVE LOGITS
    -zA
    0.07
     �
    0.07
     MethodInvocation
    0.06
    .DropTable
    0.06
     allowable
    0.06
    ẻ
    0.06
    具有
    0.06
    icularly
    0.06
    --------------------------------------------------------------------------↵
    0.06
    setMax
    0.06
    Act Density 0.000%

    No Known Activations