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

    Neuronpedia

    INDEX
    Explanations

    all nights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.72
     danni
    0.70
    .
    0.70
    0.70
     слабы
    0.67
     splashed
    0.66
    ין
    0.64
     времени
    0.64
     irradiated
    0.63
    ţă
    0.63
    POSITIVE LOGITS
    0
    1.07
     that
    0.98
    1
    0.97
    As
    0.94
    It
    0.90
    h
    0.87
    On
    0.85
    In
    0.84
    that
    0.82
    There
    0.80
    Act Density 0.244%

    No Known Activations