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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scorn
    -0.06
    stav
    -0.06
     Lod
    -0.06
     ResourceType
    -0.06
     jub
    -0.06
    _L
    -0.06
    Division
    -0.06
    .Register
    -0.06
     škol
    -0.06
     ulus
    -0.05
    POSITIVE LOGITS
    "?↵↵
    0.07
    ège
    0.07
    摄
    0.07
     پرونده
    0.07
     أمريكي
    0.07
     Ein
    0.06
    (aux
    0.06
    TeX
    0.06
     Zahl
    0.06
     stickers
    0.06
    Act Density 0.001%

    No Known Activations