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

    Neuronpedia

    INDEX
    Explanations

    News aggregation and submissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出身
    -0.08
    _VOID
    -0.08
    即便
    -0.07
    万博
    -0.07
    黛
    -0.07
    看不见
    -0.07
     unique
    -0.07
     aloud
    -0.07
    /locale
    -0.06
    逆转
    -0.06
    POSITIVE LOGITS
    ضل
    0.07
    ombs
    0.07
    	↵↵↵
    0.07
    olas
    0.07
    Cong
    0.07
     zz
    0.07
     Cheers
    0.07
    ouple
    0.07
    \Configuration
    0.07
    ży
    0.06
    Act Density 0.016%

    No Known Activations