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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uits
    -0.27
    аÑĨион
    -0.26
    standen
    -0.26
    amilies
    -0.25
    åĬŁçİĩ
    -0.25
    bsites
    -0.25
    -san
    -0.25
    zeichnet
    -0.24
    æĸĩåĮĸåºķèķ´
    -0.24
    utta
    -0.24
    POSITIVE LOGITS
     enough
    0.33
    nown
    0.30
    åıªåī©
    0.29
     and
    0.27
    ENDED
    0.27
     writ
    0.25
    spe
    0.25
    spr
    0.25
    olean
    0.25
    inate
    0.24
    Act Density 0.008%

    No Known Activations