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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getParam
    -0.07
    ادة
    -0.07
    inski
    -0.06
    DOM
    -0.06
    acción
    -0.06
    ashboard
    -0.06
    रत
    -0.06
    Ｏ
    -0.06
    学习
    -0.06
    該
    -0.06
    POSITIVE LOGITS
     Giant
    0.08
     Follow
    0.07
     Prince
    0.07
    мерикан
    0.06
    _cls
    0.06
     Marcus
    0.06
     Netherlands
    0.06
     Braves
    0.06
    .Nome
    0.06
     Comb
    0.06
    Act Density 0.012%

    No Known Activations