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

    Neuronpedia

    INDEX
    Explanations

    either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utor
    -0.07
     Revision
    -0.07
    代表团
    -0.06
    ではありません
    -0.06
     hak
    -0.06
    숙
    -0.06
    }):
    -0.06
    _ENCODING
    -0.06
    พฤศจ
    -0.06
    健
    -0.06
    POSITIVE LOGITS
    _ls
    0.07
    Breaking
    0.07
     gangbang
    0.07
     merging
    0.06
           
    0.06
    淘汰
    0.06
     Gina
    0.06
    uraa
    0.06
    打出
    0.06
     전체
    0.06
    Act Density 0.000%

    No Known Activations