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

    Neuronpedia

    INDEX
    Explanations

    Dion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    体贴
    -0.07
    直至
    -0.07
    Robot
    -0.07
    periments
    -0.07
    腩
    -0.07
    Reduc
    -0.07
    مز
    -0.06
    _MAY
    -0.06
     Parkinson
    -0.06
    贴
    -0.06
    POSITIVE LOGITS
    Ō
    0.08
     미래
    0.08
     Fore
    0.08
    โฟ
    0.07
    илась
    0.07
     Keith
    0.07
    ܩ
    0.07
     quoting
    0.07
     mapping
    0.07
     Kön
    0.07
    Act Density 0.003%

    No Known Activations