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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    姆
    -0.07
    .J
    -0.07
     SUPER
    -0.07
     Jeffrey
    -0.06
    这部
    -0.06
    党的
    -0.06
    -J
    -0.06
    =[],
    -0.06
    adi
    -0.06
    מקור
    -0.06
    POSITIVE LOGITS
    _rw
    0.07
     fırsat
    0.07
     Contractors
    0.07
    Lines
    0.07
    化解
    0.07
    兴趣
    0.07
     settle
    0.07
    عراض
    0.07
     commenced
    0.06
    categorias
    0.06
    Act Density 0.215%

    No Known Activations