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

    Neuronpedia

    INDEX
    Explanations

    injection, avoid, right, sensor, solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    点
    0.51
    Ç
    0.49
    图
    0.48
    比
    0.48
    乙
    0.48
    ت
    0.47
    ET
    0.46
    ций
    0.46
    天
    0.46
    游戏
    0.45
    POSITIVE LOGITS
    esor
    0.45
     suivante
    0.45
     두고
    0.44
    bins
    0.43
    ările
    0.41
    ROff
    0.40
     नस्
    0.40
    ald
    0.40
    endon
    0.40
     হ
    0.39
    Act Density 0.001%

    No Known Activations