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

    Neuronpedia

    INDEX
    Explanations

    circ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    微博
    -0.08
    (Boolean
    -0.07
    For
    -0.07
     LANG
    -0.07
    @Injectable
    -0.07
    Opacity
    -0.07
    .sales
    -0.07
    .Init
    -0.07
     morality
    -0.06
    .Set
    -0.06
    POSITIVE LOGITS
    ürü
    0.07
    (bg
    0.07
     tersebut
    0.07
    ң
    0.07
     exhaust
    0.06
     Civil
    0.06
    芤
    0.06
    TÜ
    0.06
    ʥ
    0.06
    ᭺
    0.06
    Act Density 0.005%

    No Known Activations