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

    Neuronpedia

    INDEX
    Explanations

    Licensed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Below
    -0.07
     мужчин
    -0.07
    _pow
    -0.07
     energ
    -0.07
    低温
    -0.07
     UnityEditor
    -0.06
    divider
    -0.06
    .Selenium
    -0.06
    郁
    -0.06
    idious
    -0.06
    POSITIVE LOGITS
    教训
    0.07
     sollte
    0.07
    改革开放
    0.07
    uggested
    0.07
     rationale
    0.07
    حط
    0.06
    _HELPER
    0.06
    ガイ
    0.06
    adero
    0.06
    imeline
    0.06
    Act Density 0.000%

    No Known Activations