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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acariy
    0.31
    ლებიც
    0.30
    ന്വേഷ
    0.29
     المصفوفه
    0.29
    केमॉन
    0.28
     शीजान
    0.28
     Elektrokhimiya
    0.27
    위원회
    0.27
    <unused1687>
    0.27
    제목
    0.27
    POSITIVE LOGITS
    0
    0.48
    5
    0.47
    7
    0.41
    3
    0.41
    4
    0.41
    6
    0.39
    2
    0.39
    8
    0.39
     +
    0.38
     cm
    0.36
    Act Density 0.114%

    No Known Activations