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

    Neuronpedia

    INDEX
    Explanations

    crow and Chron/Cron prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Liao
    1.02
    savvy
    0.97
     fundamental
    0.94
     amministrat
    0.91
    ونم
    0.90
     prompt
    0.88
     Surreal
    0.87
     Ludwig
    0.87
    IGH
    0.87
     ferrovi
    0.86
    POSITIVE LOGITS
    oked
    1.03
    plist
    0.90
    idation
    0.86
    ucle
    0.82
    স্ব
    0.82
    ోధ
    0.80
    ₕ
    0.80
    invoke
    0.79
    𝙄
    0.75
    炬
    0.75
    Act Density 0.052%

    No Known Activations