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

    Neuronpedia

    INDEX
    Explanations

    86

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gujarat
    -0.10
    special
    -0.07
    $val
    -0.07
     genome
    -0.06
    _Al
    -0.06
    帖
    -0.06
    *>
    -0.06
     returns
    -0.06
     additives
    -0.06
    trad
    -0.06
    POSITIVE LOGITS
     efficiently
    0.07
    <iostream
    0.07
     VB
    0.06
     trot
    0.06
    长
    0.06
     Waist
    0.06
    原
    0.06
     obtaining
    0.06
    owners
    0.06
    olin
    0.06
    Act Density 0.002%

    No Known Activations