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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragile
    -0.07
     fifty
    -0.06
     Refresh
    -0.06
     twenty
    -0.06
    ”，
    -0.06
     stif
    -0.06
     Californ
    -0.06
     elast
    -0.06
    FileDialog
    -0.06
    Storage
    -0.06
    POSITIVE LOGITS
    λμ
    0.07
    ,)↵
    0.06
     inform
    0.06
    'd
    0.06
    -alist
    0.06
    UDGE
    0.06
     Hum
    0.06
    نسان
    0.06
    세
    0.06
     peanut
    0.06
    Act Density 0.004%

    No Known Activations