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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Feature
    -0.07
     tradition
    -0.07
    Fx
    -0.06
    INCREMENT
    -0.06
     ofrece
    -0.06
    我們
    -0.06
    kh
    -0.06
    _final
    -0.06
     pian
    -0.06
     junit
    -0.06
    POSITIVE LOGITS
     clown
    0.07
     perfume
    0.06
    اءات
    0.06
    ，不
    0.06
     sue
    0.06
    Img
    0.06
     انتخاب
    0.06
    ULT
    0.06
    挺
    0.06
    kehr
    0.06
    Act Density 0.004%

    No Known Activations