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

    Neuronpedia

    INDEX
    Explanations

    integration hub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    2.52
    ה
    2.39
    У
    2.23
    い
    2.16
    ل
    2.03
    m
    2.02
    ن
    2.02
    ch
    1.98
    न
    1.97
    ל
    1.88
    POSITIVE LOGITS
     খাঁর
    1.69
     góc
    1.66
    cf
    1.59
    ፍተኛ
    1.58
    ма
    1.55
    tip
    1.55
    celli
    1.53
     latérales
    1.52
    tone
    1.51
    ى
    1.48
    Act Density 0.001%

    No Known Activations