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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inoltre
    -0.07
     ayudar
    -0.07
     sorg
    -0.07
     COPYRIGHT
    -0.07
     Fa
    -0.07
    竹
    -0.07
    好友
    -0.07
     bullets
    -0.07
     helpu
    -0.07
    Mining
    -0.07
    POSITIVE LOGITS
     viable
    0.09
     Нам
    0.08
     정상
    0.08
     consomm
    0.08
     dc
    0.08
     gaz
    0.08
    _valid
    0.07
     penis
    0.07
     taxable
    0.07
     candidat
    0.07
    Act Density 0.052%

    No Known Activations