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
    transform
    -0.07
     Hoffman
    -0.07
    _BUF
    -0.07
     {{$
    -0.07
    Formatter
    -0.07
     jeżeli
    -0.06
    摄影
    -0.06
     Educational
    -0.06
     bữa
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    <Character
    0.08
    -fashioned
    0.08
    	Runtime
    0.08
    得起
    0.07
     Fits
    0.07
     Rub
    0.07
    (length
    0.07
    geme
    0.07
    ليل
    0.07
    𬬮
    0.06
    Act Density 0.014%

    No Known Activations