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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。例如
    -0.10
     ponta
    -0.07
    旨
    -0.07
    teilungen
    -0.07
    ，例如
    -0.07
     চিন
    -0.07
    ONLY
    -0.07
     باشد
    -0.07
     આધાર
    -0.07
    Reduction
    -0.07
    POSITIVE LOGITS
     fights
    0.09
     schließlich
    0.09
     ritual
    0.09
     posteriormente
    0.08
     Elf
    0.08
     Cartoon
    0.08
     elf
    0.08
     aftermath
    0.08
     девушка
    0.08
     flee
    0.08
    Act Density 0.031%

    No Known Activations