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

    Neuronpedia

    INDEX
    Explanations

    navigation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sigma
    0.98
    ्‍य
    0.95
    s
    0.94
    ς
    0.93
    懑
    0.91
     其他
    0.91
    sı
    0.90
    ्‍यादा
    0.89
    ય
    0.88
     continue
    0.88
    POSITIVE LOGITS
    вен
    0.82
    geführt
    0.80
    giving
    0.79
    чность
    0.78
    ாள
    0.77
    gesetz
    0.77
    ون
    0.75
    grund
    0.72
    enschaft
    0.71
    じて
    0.71
    Act Density 0.000%

    No Known Activations