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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stop
    -0.07
     décor
    -0.07
     stitches
    -0.07
     Dex
    -0.06
     democr
    -0.06
    ()<<"
    -0.06
     stare
    -0.06
    祐
    -0.06
    numer
    -0.06
    $date
    -0.06
    POSITIVE LOGITS
    trand
    0.07
    vement
    0.07
    有限
    0.07
     קישורים
    0.07
    决战
    0.07
    אות
    0.06
     aren
    0.06
    勇敢
    0.06
    ANT
    0.06
    ations
    0.06
    Act Density 0.036%

    No Known Activations