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

    Neuronpedia

    INDEX
    Explanations

    intact ever, by human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.13
     would
    0.96
    ses
    0.94
     (
    0.92
     was
    0.87
    ben
    0.83
     more
    0.82
     it
    0.82
     intrinsic
    0.81
    /
    0.81
    POSITIVE LOGITS
    chyné
    1.60
    ớp
    1.51
    >∞</
    1.49
     čtyř
    1.49
     sareng
    1.48
     ámbito
    1.44
    ⵚ
    1.42
     záb
    1.42
     באמצעות
    1.41
    Bechyné
    1.41
    Act Density 0.000%

    No Known Activations