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

    Neuronpedia

    INDEX
    Explanations

    qualities and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biraz
    0.63
     trochu
    0.59
     genoeg
    0.55
     või
    0.54
    なかなか
    0.53
     trochę
    0.53
     bardziej
    0.53
    または
    0.50
    꽤
    0.49
    ంచెం
    0.49
    POSITIVE LOGITS
    .)
    0.54
    .),
    0.49
     extremely
    0.49
    所謂
    0.48
    极其
    0.48
    extremely
    0.47
     (!)
    0.47
     되는
    0.46
     unregulated
    0.46
     imaginable
    0.46
    Act Density 0.295%

    No Known Activations