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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     candy
    -0.06
     civic
    -0.06
    echo
    -0.06
     Front
    -0.06
     dokun
    -0.06
     bahis
    -0.06
     Press
    -0.06
    ौल
    -0.06
     FormData
    -0.06
     {*}
    -0.06
    POSITIVE LOGITS
    =torch
    0.08
    _embedding
    0.07
    setState
    0.07
    λε
    0.07
     �
    0.07
     Pří
    0.07
     предполаг
    0.07
    ению
    0.07
    	define
    0.07
     전세
    0.07
    Act Density 0.003%

    No Known Activations