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

    Neuronpedia

    INDEX
    Explanations

    random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bodies
    -0.07
    .DO
    -0.06
     обрат
    -0.06
     Pere
    -0.06
     Publication
    -0.06
     Witch
    -0.06
     pregnancies
    -0.06
     rolled
    -0.06
    amodel
    -0.06
     Stokes
    -0.06
    POSITIVE LOGITS
    ceipt
    0.07
    تب
    0.06
    49
    0.06
    ッド
    0.06
    戲
    0.06
     솔
    0.06
    -good
    0.06
    σω
    0.06
    ات
    0.06
     现
    0.06
    Act Density 0.000%

    No Known Activations