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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ses
    0.62
    ners
    0.62
    sa
    0.56
    st
    0.52
     Car
    0.50
    person
    0.50
    saver
    0.49
    s
    0.49
    xiety
    0.48
    screen
    0.48
    POSITIVE LOGITS
     cromosoma
    0.52
    對方
    0.48
     canaux
    0.47
    理論
    0.47
     dotato
    0.46
     donnée
    0.45
     articol
    0.45
     riserv
    0.45
    كنولوج
    0.45
    地下
    0.44
    Act Density 0.109%

    No Known Activations