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

    Neuronpedia

    INDEX
    Explanations

    probability and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensory
    0.38
    Vo
    0.38
    health
    0.37
    大学
    0.37
    Health
    0.37
    струк
    0.37
    деся
    0.37
    矯
    0.37
    otica
    0.36
     Burgh
    0.36
    POSITIVE LOGITS
     probability
    0.76
     Probability
    0.71
    probability
    0.66
    Probability
    0.65
     probabilidad
    0.64
     probabilities
    0.63
     вероятность
    0.59
    Prob
    0.58
     Prob
    0.57
     확률
    0.56
    Act Density 0.043%

    No Known Activations