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

    Neuronpedia

    INDEX
    Explanations

    goes into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ാനം
    0.42
    rera
    0.41
     追加
    0.39
    كز
    0.39
    嫡
    0.38
     添加
    0.38
    addDigit
    0.37
     subtracting
    0.37
     compensating
    0.37
    rer
    0.37
    POSITIVE LOGITS
     들어가
    0.54
     into
    0.53
     vào
    0.52
    เข้าไป
    0.48
     Into
    0.46
    Into
    0.45
     INTO
    0.42
     malades
    0.42
     इनटू
    0.41
     içine
    0.40
    Act Density 0.003%

    No Known Activations