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

    Neuronpedia

    INDEX
    Explanations

    Names and Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hdl
    -0.07
     Accuracy
    -0.06
    	SP
    -0.06
     #
↵
    -0.06
    _intf
    -0.06
    }
↵
↵
    -0.06
     پایین
    -0.06
     pri
    -0.06
     RAD
    -0.06
     Batt
    -0.06
    POSITIVE LOGITS
     noexcept
    0.07
    -dem
    0.06
    ými
    0.06
     deaths
    0.06
     Negot
    0.06
    :]↵
    0.06
    \Unit
    0.06
     jeu
    0.06
     Bibli
    0.06
    iples
    0.06
    Act Density 0.090%

    No Known Activations