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
    ​↵↵
    -0.07
     expended
    -0.07
     Snowden
    -0.07
    	write
    -0.07
     trans
    -0.06
     data
    -0.06
    투
    -0.06
    metis
    -0.06
     Tele
    -0.06
    ober
    -0.06
    POSITIVE LOGITS
     Yosh
    0.07
     abl
    0.07
     �
    0.07
    oso
    0.07
     Legacy
    0.06
     Ngb
    0.06
     -(
    0.06
     Sasha
    0.06
     내가
    0.06
    ,np
    0.06
    Act Density 0.045%

    No Known Activations