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

    Neuronpedia

    INDEX
    Explanations

    distribution and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चर्स
    0.71
    ➸
    0.69
    勇
    0.69
    енча
    0.67
    炖
    0.66
     उबर
    0.66
     Bruges
    0.64
    ㇁
    0.64
    阳
    0.64
     подъ
    0.64
    POSITIVE LOGITS
     distribution
    5.58
     Distribution
    5.28
    Distribution
    5.18
    distribution
    5.01
     distributions
    5.01
     distribute
    5.00
     distributed
    4.83
     distributing
    4.82
     distrib
    4.76
     distribu
    4.70
    Act Density 0.228%

    No Known Activations