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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Minecraft
    -0.07
    常に
    -0.07
     XIII
    -0.07
    uniacid
    -0.07
    否认
    -0.07
    固然
    -0.06
    azo
    -0.06
    私が
    -0.06
    ӂ
    -0.06
    베
    -0.06
    POSITIVE LOGITS
     accountable
    0.07
    诰
    0.07
    发
    0.07
     Highlights
    0.07
     Accent
    0.07
     compassionate
    0.06
    科普
    0.06
    _PERSON
    0.06
     ripping
    0.06
     dramatic
    0.06
    Act Density 0.009%

    No Known Activations