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

    Neuronpedia

    INDEX
    Explanations

    source code and identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     организма
    0.31
     توسط
    0.30
    加坡
    0.30
     partícula
    0.29
    其他
    0.29
     ممکن
    0.29
     enfermedad
    0.29
     сигнала
    0.29
     زيت
    0.29
    ینو
    0.28
    POSITIVE LOGITS
     for
    0.51
    at
    0.41
    al
    0.39
     Children
    0.37
    ad
    0.37
    ar
    0.36
     For
    0.36
    p
    0.36
    ou
    0.36
     destination
    0.34
    Act Density 0.149%

    No Known Activations