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

    Neuronpedia

    INDEX
    Explanations

    say "bets"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (menu
    -0.07
     Guatemala
    -0.07
    Prof
    -0.06
     боли
    -0.06
    vre
    -0.06
     datap
    -0.06
     مردم
    -0.06
     районе
    -0.06
     mankind
    -0.06
     moved
    -0.06
    POSITIVE LOGITS
    (chr
    0.07
     matched
    0.06
    Transpose
    0.06
     finalize
    0.06
    ,’’
    0.06
     THANK
    0.06
     �
    0.06
     kış
    0.06
    _man
    0.06
     kami
    0.06
    Act Density 0.055%

    No Known Activations