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

    Neuronpedia

    INDEX
    Explanations

    podcast interviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Margin
    0.50
     précédent
    0.45
     рукой
    0.43
     видел
    0.43
     Secondly
    0.42
     Parfum
    0.42
     үш
    0.42
     Счет
    0.42
    ২০
    0.41
    Numbered
    0.41
    POSITIVE LOGITS
    vy
    0.43
    co
    0.42
    us
    0.42
    f
    0.42
    烘
    0.41
    x
    0.41
    ch
    0.41
    le
    0.40
     storms
    0.40
     lazy
    0.40
    Act Density 0.000%

    No Known Activations