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

    Neuronpedia

    INDEX
    Explanations

    brands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     settles
    -0.09
     indispensable
    -0.08
    (binary
    -0.08
    .binary
    -0.08
    !!!↵↵
    -0.07
     binary
    -0.07
     paran
    -0.07
    -IN
    -0.07
    -ה
    -0.07
     (_.
    -0.07
    POSITIVE LOGITS
     Starbucks
    0.10
     உள்ள
    0.08
     Lyft
    0.08
    ையின்
    0.07
     uchar
    0.07
    ையை
    0.07
     Tokens
    0.07
    ல்
    0.07
    $tmp
    0.07
    classmethod
    0.07
    Act Density 0.006%

    No Known Activations