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

    Neuronpedia

    INDEX
    Explanations

    list/array

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     программ
    -0.07
    уницип
    -0.07
     intentions
    -0.06
    这一次
    -0.06
    脱发
    -0.06
    蹿
    -0.06
     bron
    -0.06
    腸
    -0.06
    珊瑚
    -0.06
     tests
    -0.06
    POSITIVE LOGITS
    marshall
    0.07
    .tm
    0.07
    .getDay
    0.07
    рез
    0.07
    dığında
    0.07
     aynı
    0.06
     incorrect
    0.06
    haven
    0.06
     shifted
    0.06
    灵活性
    0.06
    Act Density 0.014%

    No Known Activations