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

    Neuronpedia

    INDEX
    Explanations

    dispute resolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beit
    -0.07
     Levy
    -0.07
     massac
    -0.06
    rick
    -0.06
    abb
    -0.06
    ру
    -0.06
     така
    -0.06
    hor
    -0.06
     開
    -0.06
     Kennedy
    -0.06
    POSITIVE LOGITS
    илась
    0.07
    ือน
    0.07
    +xml
    0.06
    زة
    0.06
     ----------------------------------------------------------------------------↵
    0.06
     düzenli
    0.06
    .rpc
    0.06
     Laz
    0.06
    ofilm
    0.06
    single
    0.06
    Act Density 0.009%

    No Known Activations