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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ache
    -0.08
     הילד
    -0.08
    _std
    -0.07
     млн
    -0.07
     있기
    -0.07
    低位
    -0.06
     Publisher
    -0.06
    转载
    -0.06
    (tmp
    -0.06
    请你
    -0.06
    POSITIVE LOGITS
    鞍山
    0.07
    _Metadata
    0.07
    //------------------------------------------------------------------------------------------------
    0.07
     ]);↵↵
    0.07
    then
    0.07
    Sprites
    0.07
    鬷
    0.07
    ṣ
    0.07
    icopt
    0.07
    )";
↵
    0.07
    Act Density 0.034%

    No Known Activations