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

    Neuronpedia

    INDEX
    Explanations

    devised

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的颜色
    -0.07
     Friday
    -0.07
    提到
    -0.07
    HashMap
    -0.07
     fontFamily
    -0.07
    نطق
    -0.07
     الدراسي
    -0.07
    所以他
    -0.07
    atorio
    -0.06
     FileInputStream
    -0.06
    POSITIVE LOGITS
    徕
    0.07
    ложить
    0.07
    ё
    0.07
    (players
    0.07
     maken
    0.06
     Rapid
    0.06
     �
    0.06
    赢得了
    0.06
    .web
    0.06
    .Patient
    0.06
    Act Density 0.004%

    No Known Activations