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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    original
    -0.07
     anglais
    -0.07
     h
    -0.06
    *d
    -0.06
    頁
    -0.06
     Overrides
    -0.06
    -transparent
    -0.06
     shar
    -0.06
     않을
    -0.06
     Restoration
    -0.06
    POSITIVE LOGITS
     Www
    0.07
    oms
    0.06
    /manual
    0.06
     respecting
    0.06
    .“
    0.06
    Art
    0.06
    Prom
    0.06
    uesto
    0.06
     Associate
    0.06
    udiant
    0.06
    Act Density 0.005%

    No Known Activations