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

    Neuronpedia

    INDEX
    Explanations

    all rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    1.08
    il
    1.04
    ور
    0.87
    ara
    0.86
    ı
    0.86
    ين
    0.81
    á
    0.80
    im
    0.79
     Pawn
    0.78
    ou
    0.77
    POSITIVE LOGITS
    ν
    0.92
    Влади
    0.88
    ɦ
    0.87
    oğlu
    0.85
     weinig
    0.85
    ɖ
    0.85
    िफिशियल
    0.84
     fabricating
    0.83
     polymer
    0.82
     limitaciones
    0.82
    Act Density 0.017%

    No Known Activations