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

    Neuronpedia

    INDEX
    Explanations

    .basicConfig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Λ
    -0.07
    拼
    -0.07
     congressional
    -0.07
     BILL
    -0.07
    ouchers
    -0.07
     Burton
    -0.07
     tipping
    -0.07
    atively
    -0.07
    wł
    -0.06
    犏
    -0.06
    POSITIVE LOGITS
     despair
    0.07
    どんな
    0.07
    _request
    0.06
    갖
    0.06
    кая
    0.06
    不良
    0.06
     danych
    0.06
     Common
    0.06
    ال
    0.06
    硁
    0.06
    Act Density 0.000%

    No Known Activations