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

    Neuronpedia

    INDEX
    Explanations

    dates and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.47
     MARK
    0.43
     сообщи
    0.43
    ized
    0.41
    E
    0.41
    (
    0.40
    sh
    0.40
     čas
    0.40
    ’
    0.40
    agedy
    0.39
    POSITIVE LOGITS
    л
    0.86
    ט
    0.54
    ल
    0.52
    ল
    0.51
    ב
    0.51
    લ
    0.49
    ட
    0.49
    কে
    0.48
    ي
    0.48
     an
    0.47
    Act Density 0.006%

    No Known Activations