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

    Neuronpedia

    INDEX
    Explanations

    William Afton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diantaranya
    0.43
     luas
    0.43
     those
    0.42
    "]:
    0.41
     revolt
    0.41
     படிக்க
    0.41
     происхождения
    0.41
     humana
    0.41
     her
    0.41
     ее
    0.41
    POSITIVE LOGITS
    MIER
    0.48
     კიდ
    0.47
    ｮ
    0.46
    Uint
    0.45
    ERV
    0.45
    يمي
    0.45
    unkt
    0.44
    ált
    0.43
    AY
    0.43
     تكون
    0.43
    Act Density 0.000%

    No Known Activations