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

    Neuronpedia

    INDEX
    Explanations

    lists, descriptions, or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.55
    ي
    0.55
    of
    0.54
     reach
    0.52
     Of
    0.52
    T
    0.49
    B
    0.47
    to
    0.46
     of
    0.46
     _
    0.46
    POSITIVE LOGITS
     परिवर्तन
    0.44
    ierre
    0.43
     변화
    0.43
    ก่
    0.42
     ま
    0.41
    ିକ
    0.41
     পরিবেশ
    0.41
    .'</
    0.41
     sıcak
    0.40
    畩
    0.40
    Act Density 0.001%

    No Known Activations