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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns/place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ará
    -0.07
     エ
    -0.06
    odí
    -0.06
     nfl
    -0.06
     Zoo
    -0.06
    	error
    -0.06
    pra
    -0.06
     retrieving
    -0.06
     august
    -0.06
    dit
    -0.06
    POSITIVE LOGITS
     пів
    0.07
     XBOOLE
    0.07
     manos
    0.07
     ########.
    0.07
    .FONT
    0.06
    ])))↵
    0.06
    -----------↵
    0.06
    :]:↵
    0.06
    （笑
    0.06
    -----------*/↵
    0.06
    Act Density 0.272%

    No Known Activations