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

    Neuronpedia

    INDEX
    Explanations

    Master's degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.74
    mensaje
    0.73
     dijual
    0.72
     the
    0.71
    ک
    0.69
    ﺍ
    0.68
    ت
    0.68
    ادية
    0.67
    ท์
    0.66
    ський
    0.66
    POSITIVE LOGITS
    。"
    0.66
    。
    0.63
    𝑪
    0.63
    。(
    0.61
    нологи
    0.58
    ↵↵
    0.56
    0.56
    。...
    0.54
    釟
    0.53
    这类
    0.53
    Act Density 0.000%

    No Known Activations