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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Î
    -0.10
     frequ
    -0.08
     �
    -0.08
    研
    -0.07
     fort
    -0.07
    Â
    -0.07
    Î
    -0.07
    â
    -0.07
     â
    -0.07
     Kra
    -0.07
    POSITIVE LOGITS
    FSM
    0.09
     нет
    0.09
     fasta
    0.08
    ghị
    0.08
    ась
    0.08
     cenas
    0.08
     gelang
    0.07
     jie
    0.07
     tuv
    0.07
    咪
    0.07
    Act Density 0.019%

    No Known Activations