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

    Neuronpedia

    INDEX
    Explanations

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.70
    ف
    0.64
    س
    0.64
    with
    0.59
    ال
    0.57
    ك
    0.55
    세계
    0.54
    ج
    0.54
    ش
    0.54
    Від
    0.52
    POSITIVE LOGITS
    ль
    0.44
     ತಿಳ
    0.43
    lessis
    0.42
    esha
    0.42
     FERN
    0.42
     работать
    0.41
     VAR
    0.41
    elere
    0.41
     Schuster
    0.40
     INCREASE
    0.40
    Act Density 0.041%

    No Known Activations