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

    Neuronpedia

    INDEX
    Explanations

    programming and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istribute
    -0.08
    表
    -0.07
    羊
    -0.07
    羲
    -0.07
     ut
    -0.07
    乌
    -0.07
     -------------
    -0.07
     axes
    -0.07
     состоя
    -0.07
    �
    -0.06
    POSITIVE LOGITS
    _LT
    0.06
    ܢ
    0.06
     conceivable
    0.06
     דברים
    0.06
    نبي
    0.06
    ﭯ
    0.06
     revolving
    0.06
     Finn
    0.06
     khu
    0.06
    нский
    0.06
    Act Density 0.087%

    No Known Activations