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

    Neuronpedia

    INDEX
    Explanations

    numbers/measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.82
     and
    0.78
     or
    0.70
     from
    0.68
     s
    0.68
     all
    0.64
     medals
    0.64
     be
    0.63
    and
    0.61
     eagles
    0.60
    POSITIVE LOGITS
    arı
    0.62
    ového
    0.52
    تباينه
    0.52
    ҽ
    0.50
    penup
    0.49
    laublich
    0.48
     букмекерлик
    0.48
    elijkheid
    0.47
     función
    0.47
    erende
    0.47
    Act Density 0.777%

    No Known Activations