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

    Neuronpedia

    INDEX
    Explanations

    latest data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    myTransform
    0.43
    suspended
    0.43
     pemas
    0.42
    转型
    0.42
     desvent
    0.42
     trasform
    0.41
     échanc
    0.41
    运营商
    0.41
    咀
    0.41
     konk
    0.40
    POSITIVE LOGITS
    BGR
    0.35
    ferences
    0.35
    ву
    0.34
     سلي
    0.33
    Те
    0.33
    Determ
    0.33
     reproducible
    0.33
     වූ
    0.33
     Тео
    0.33
    ichen
    0.32
    Act Density 0.000%

    No Known Activations