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

    Neuronpedia

    INDEX
    Explanations

    ((

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bí
    -0.07
    悄
    -0.07
     Morr
    -0.07
     Albany
    -0.07
     imageURL
    -0.07
     bör
    -0.06
    慣れ
    -0.06
     wygląda
    -0.06
     már
    -0.06
    胡子
    -0.06
    POSITIVE LOGITS
    entities
    0.08
    athe
    0.07
    erie
    0.07
    當
    0.07
    rophy
    0.07
    VALID
    0.07
    by
    0.07
    传统
    0.07
     tum
    0.07
    топ
    0.07
    Act Density 0.002%

    No Known Activations