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

    Neuronpedia

    INDEX
    Explanations

    create scoring chances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गण
    0.39
    afio
    0.39
     укреп
    0.38
     일단
    0.38
    FixedHeight
    0.38
    岱
    0.37
    __(/*!
    0.37
    retreat
    0.37
    িতে
    0.37
    線上
    0.36
    POSITIVE LOGITS
     chances
    1.32
     Chances
    1.14
     chance
    1.01
     Chancen
    0.95
    chance
    0.83
     Chance
    0.79
    Chance
    0.76
     peluang
    0.73
     шан
    0.72
     probability
    0.71
    Act Density 0.004%

    No Known Activations