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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    огда
    -0.07
     Wolfe
    -0.07
     пере
    -0.07
    чик
    -0.06
    斗
    -0.06
    Emoji
    -0.06
     徒
    -0.06
    ंबर
    -0.06
     Friedrich
    -0.06
     zza
    -0.06
    POSITIVE LOGITS
     malaysia
    0.06
     Strom
    0.06
    supports
    0.06
    وز
    0.06
    Mac
    0.06
     korum
    0.06
     지역
    0.06
    db
    0.06
    670
    0.06
     Man
    0.06
    Act Density 0.044%

    No Known Activations