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

    Neuronpedia

    INDEX
    Explanations

    give a sense of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.67
     an
    0.61
     for
    0.59
     A
    0.59
     An
    0.58
    a
    0.58
     a
    0.55
    an
    0.55
    ath
    0.52
    aya
    0.51
    POSITIVE LOGITS
    🤏
    0.56
    ч
    0.55
     것도
    0.54
    씩
    0.54
     όχι
    0.51
    он
    0.49
    ിച്ചത്
    0.49
     tinge
    0.48
     jų
    0.48
    ями
    0.48
    Act Density 0.179%

    No Known Activations