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

    Neuronpedia

    INDEX
    Explanations

    various languages and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    words that choose or specify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.85
    h
    0.80
    (
    0.79
    m
    0.77
    ON
    0.74
    OF
    0.72
    AM
    0.71
    l
    0.70
    HEN
    0.69
    "
    0.68
    POSITIVE LOGITS
    ή
    0.63
    ों
    0.56
    的价格
    0.53
    0.52
     étroite
    0.52
    ки
    0.51
     tâm
    0.50
     thậm
    0.50
    𝑡
    0.50
     maximale
    0.49
    Act Density 0.321%

    No Known Activations