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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pokud
    -0.07
    _DEFIN
    -0.07
     dou
    -0.07
    ٥
    -0.07
    Ing
    -0.07
     initial
    -0.06
    (Model
    -0.06
    ██
    -0.06
     runtime
    -0.06
     richTextBox
    -0.06
    POSITIVE LOGITS
     неск
    0.07
    ΟΥΣ
    0.07
    पत
    0.06
    كون
    0.06
     flew
    0.06
     Сер
    0.06
    enment
    0.06
     �
    0.06
    цуз
    0.06
    닥
    0.06
    Act Density 0.172%

    No Known Activations