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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tavs
    -0.06
    ange
    -0.06
    anger
    -0.06
    BTTag
    -0.06
     indexer
    -0.06
    /Set
    -0.06
     recursion
    -0.06
     misinformation
    -0.06
    	RTLR
    -0.06
    	rs
    -0.06
    POSITIVE LOGITS
    _where
    0.07
     �
    0.07
     مدت
    0.07
    atorio
    0.06
    VIDEO
    0.06
    _SM
    0.06
    وزيع
    0.06
     Www
    0.06
     Seamless
    0.06
    '↵↵
    0.06
    Act Density 0.042%

    No Known Activations