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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    修补
    -0.08
     FLAG
    -0.07
    捉
    -0.07
    ','".$
    -0.07
     va
    -0.07
     Cipher
    -0.07
     항
    -0.07
    ники
    -0.07
    班长
    -0.07
    控
    -0.06
    POSITIVE LOGITS
    쉿
    0.08
    !)↵↵
    0.07
    -peer
    0.07
     Murdoch
    0.07
    _COMMENT
    0.07
    );}↵↵
    0.07
    emens
    0.07
    学
    0.07
     Algeria
    0.06
    arian
    0.06
    Act Density 0.002%

    No Known Activations