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

    Neuronpedia

    INDEX
    Explanations

    tokens followed by slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x99>
    0.82
     Waldo
    0.82
     Bender
    0.80
     ALPINE
    0.78
    ცხ
    0.78
     ಮುಂದೆ
    0.76
    зья
    0.73
    悟
    0.70
    ‌്
    0.70
     टेंशन
    0.70
    POSITIVE LOGITS
     /
    2.24
    /
    1.76
    `/
    1.59
     `/
    1.57
     '/
    1.51
     "/
    1.46
    '/
    1.42
    "/
    1.41
    )/
    1.39
    -/
    1.38
    Act Density 0.190%

    No Known Activations