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
    oten
    -0.07
     whiskey
    -0.06
    Open
    -0.06
     Sorted
    -0.06
     Divider
    -0.06
    *np
    -0.06
    .expr
    -0.06
    replaceAll
    -0.06
    Youtube
    -0.06
     Beverly
    -0.06
    POSITIVE LOGITS
    ）↵↵
    0.07
    _play
    0.06
    $l
    0.06
    fib
    0.06
    (base
    0.06
     ],
↵
    0.06
     بالن
    0.06
     що
    0.06
    676
    0.06
     NSW
    0.06
    Act Density 0.077%

    No Known Activations