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

    Neuronpedia

    INDEX
    Explanations

    probability and odds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Frankenstein
    0.89
    斧
    0.82
     তেল
    0.81
     Culinary
    0.76
     건축
    0.76
     স্থাপত্য
    0.75
     parsley
    0.75
    ક્રિય
    0.75
    USERNAME
    0.74
     肉
    0.74
    POSITIVE LOGITS
     probabilities
    2.57
     probability
    2.52
     probabilistic
    2.50
    Probability
    2.40
     Probability
    2.35
     statistical
    2.32
    probability
    2.19
    概率
    2.18
     probabilidad
    2.14
    probabilities
    2.11
    Act Density 0.559%

    No Known Activations