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
     pag
    -0.07
     steward
    -0.07
     growers
    -0.07
     مقدار
    -0.07
    	max
    -0.06
     Wort
    -0.06
     Loch
    -0.06
     rubble
    -0.06
     diarrhea
    -0.06
     printing
    -0.06
    POSITIVE LOGITS
     fiz
    0.07
    .primary
    0.06
    Cheers
    0.06
    $(".
    0.06
    ################################################################################
    0.06
    ovně
    0.06
    その他
    0.06
    ูรณ
    0.06
     �
    0.06
    prus
    0.06
    Act Density 0.023%

    No Known Activations