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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lend
    -0.08
     Wells
    -0.07
     cj
    -0.07
    ernet
    -0.07
     kesempatan
    -0.07
     денег
    -0.07
     symbolic
    -0.07
    symbol
    -0.07
     আলো
    -0.07
     Dar
    -0.07
    POSITIVE LOGITS
     ansonsten
    0.10
     બધ
    0.10
     அனை
    0.09
    Otherwise
    0.09
     ellers
    0.08
    沒有
    0.08
    Nothing
    0.08
     સિવ
    0.08
     miscellaneous
    0.08
     otherwise
    0.08
    Act Density 0.042%

    No Known Activations