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

    Neuronpedia

    INDEX
    Explanations

    demographic statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     три
    -0.07
     הראשונים
    -0.07
     المسلحة
    -0.07
     بين
    -0.06
    Accuracy
    -0.06
    _distances
    -0.06
    Hist
    -0.06
    茹
    -0.06
    -num
    -0.06
    [])
    -0.06
    POSITIVE LOGITS
    Weak
    0.07
    ⋲
    0.07
     Güncelleme
    0.07
    芝加
    0.07
    얽
    0.06
    噙
    0.06
    总承包
    0.06
    Sources
    0.06
    أعضاء
    0.06
     американск
    0.06
    Act Density 0.000%

    No Known Activations