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

    Neuronpedia

    INDEX
    Explanations

    Text summaries/conclusions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strap
    -0.07
     Huge
    -0.07
    妭
    -0.07
    sz
    -0.07
    سرعة
    -0.07
     snag
    -0.07
     SET
    -0.07
     المص
    -0.06
    -app
    -0.06
     bamb
    -0.06
    POSITIVE LOGITS
    >".
    0.07
    坚实的
    0.07
    NSUserDefaults
    0.07
    -------------</
    0.07
    +'.
    0.07
     Fus
    0.07
    encoder
    0.06
     wonders
    0.06
    passwd
    0.06
     çıkt
    0.06
    Act Density 0.037%

    No Known Activations