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

    Neuronpedia

    INDEX
    Explanations

    doing something yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    υτό
    0.46
    icolo
    0.46
     léger
    0.43
    roben
    0.43
     cuanto
    0.42
     மொத்த
    0.42
    imètres
    0.42
     সৈন্যদের
    0.42
    ame
    0.41
     бит
    0.41
    POSITIVE LOGITS
    數字
    0.47
    භාව
    0.45
    蘑
    0.45
    ابعة
    0.45
    箱
    0.44
    Example
    0.43
    Impress
    0.42
    数字
    0.42
    有害
    0.41
    乆
    0.41
    Act Density 0.002%

    No Known Activations