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

    Neuronpedia

    INDEX
    Explanations

    URLs, especially Youtube links

    oai_token-act-pair · gemini-2.0-flash

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.01
     Normdatei
    -0.75
     autorytatywna
    -0.70
     الرياضيه
    -0.67
     linkovi
    -0.63
    ItemBackground
    -0.61
    rawDesc
    -0.61
    новниш
    -0.60
     مرئيه
    -0.60
    )».
    -0.59
    POSITIVE LOGITS
    ?
    0.59
    &
    0.48
     bArr
    0.46
     değildir
    0.43
    ↵↵
    0.42
    [
    0.41
     sì
    0.41
     devriez
    0.40
     împreună
    0.40
     Entonces
    0.39
    Act Density 3.108%

    No Known Activations