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

    Neuronpedia

    INDEX
    Explanations

    Five

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Singular
    -0.49
    B
    -0.45
    -
    -0.44
     at
    -0.44
    chan
    -0.43
     adel
    -0.42
    ngel
    -0.42
     مواليد
    -0.42
    G
    -0.41
     dandruff
    -0.41
    POSITIVE LOGITS
    tableFuture
    0.78
     للمعارف
    0.77
    <?
    0.71
    rrggbb
    0.69
    mặt
    0.68
    fromnode
    0.68
    بوابة
    0.68
    Portail
    0.65
     paramInt
    0.64
    حياتها
    0.63
    Act Density 0.000%

    No Known Activations