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

    Neuronpedia

    INDEX
    Explanations

    during

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horrified
    -0.06
    ятся
    -0.06
     été
    -0.06
     Vũ
    -0.06
    Division
    -0.06
    uil
    -0.06
    ribbon
    -0.06
     Doctrine
    -0.06
     script
    -0.06
    ellan
    -0.06
    POSITIVE LOGITS
     Regions
    0.06
    _runner
    0.06
    (cc
    0.06
     Abs
    0.06
    ุด
    0.06
    .nz
    0.06
     vivid
    0.06
    imb
    0.06
     african
    0.06
    忍
    0.06
    Act Density 0.024%

    No Known Activations