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

    Neuronpedia

    INDEX
    Explanations

    low sounds and voices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     low
    0.95
     lower
    0.90
    lower
    0.84
    低
    0.82
     низ
    0.77
     lowland
    0.77
    low
    0.76
    Low
    0.70
     Low
    0.70
     LOWER
    0.70
    POSITIVE LOGITS
    ermost
    0.82
     $(<
    0.75
     (<
    0.68
     (\<
    0.61
    (<
    0.57
    ered
    0.53
    es
    0.52
    ering
    0.49
     ebb
    0.46
    ebb
    0.45
    Act Density 0.033%

    No Known Activations