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

    Neuronpedia

    INDEX
    Explanations

    legal notices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suc
    -0.08
    苛
    -0.07
    _now
    -0.07
    书
    -0.07
    _ment
    -0.07
     miscon
    -0.07
     Famil
    -0.06
     ию
    -0.06
    ﺼ
    -0.06
    ».
    -0.06
    POSITIVE LOGITS
     theater
    0.07
    eteria
    0.07
    efs
    0.07
    령
    0.07
     đợi
    0.07
    fried
    0.07
    /fs
    0.07
    펠
    0.07
     abortion
    0.07
    ("""
    0.06
    Act Density 0.002%

    No Known Activations