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

    Neuronpedia

    INDEX
    Explanations

    AdaBoost or tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     대해서
    0.48
     nx
    0.48
     jib
    0.47
    !=
    0.46
    ರುಗ
    0.46
    뻥
    0.46
     htonl
    0.46
    ва
    0.46
     väldigt
    0.46
    ного
    0.46
    POSITIVE LOGITS
    s
    0.80
    ی
    0.72
    y
    0.61
    ي
    0.57
    ين
    0.57
    et
    0.54
    i
    0.54
    يله
    0.53
    م
    0.52
    ب
    0.52
    Act Density 0.000%

    No Known Activations