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

    Neuronpedia

    INDEX
    Explanations

    animation code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     られ
    0.61
     certes
    0.61
     bahas
    0.59
    Auch
    0.58
     상당히
    0.58
    (",
    0.55
     "',
    0.55
     moindre
    0.55
    ことも
    0.54
    টাও
    0.54
    POSITIVE LOGITS
     beat
    0.64
    beat
    0.62
     كل
    0.60
    ográficas
    0.58
     بج
    0.57
     কাল
    0.56
    rotor
    0.56
    clockwise
    0.55
    خي
    0.55
     rotating
    0.54
    Act Density 0.001%

    No Known Activations