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

    Neuronpedia

    INDEX
    Explanations

    piano music descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    0.55
    '
    0.53
    ’
    0.52
    $
    0.52
    7
    0.52
    SA
    0.50
    B
    0.49
    8
    0.48
    -
    0.47
    Us
    0.47
    POSITIVE LOGITS
    плы
    0.50
    诡
    0.49
    roidism
    0.48
    пси
    0.48
    твор
    0.47
    த்தை
    0.47
    லோச
    0.47
     adoration
    0.46
     अदा
    0.46
    лександ
    0.45
    Act Density 0.006%

    No Known Activations