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

    Neuronpedia

    INDEX
    Explanations

    cut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	boolean
    -0.07
    LAT
    -0.07
    Ca
    -0.07
    Lexer
    -0.07
     nightly
    -0.07
    ickest
    -0.07
     svého
    -0.07
     개
    -0.07
     delay
    -0.06
    Toronto
    -0.06
    POSITIVE LOGITS
    dam
    0.07
    rights
    0.07
    cken
    0.06
     Rockets
    0.06
     gigs
    0.06
     Along
    0.06
    .Info
    0.06
    сти
    0.06
    -alert
    0.06
    ;")↵
    0.06
    Act Density 0.006%

    No Known Activations