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

    Neuronpedia

    INDEX
    Explanations

    scope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flare
    -0.08
    ﻉ
    -0.07
    יקים
    -0.07
     ASSIGN
    -0.07
    ẩn
    -0.07
    .getActive
    -0.07
     killer
    -0.07
    вис
    -0.07
    urrets
    -0.06
    蘼
    -0.06
    POSITIVE LOGITS
    普遍
    0.07
    总共
    0.07
    伥
    0.07
    펍
    0.06
     אותנו
    0.06
    把她
    0.06
    把他
    0.06
    ȟ
    0.06
    _days
    0.06
     doubly
    0.06
    Act Density 0.002%

    No Known Activations