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

    Neuronpedia

    INDEX
    Explanations

    definitions and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iciencies
    1.11
     Pří
    1.07
    지만
    1.06
    くに
    1.01
    leftarrow
    0.96
     মানের
    0.96
    ्स
    0.94
    дения
    0.93
    Ｕ
    0.92
     ashamed
    0.92
    POSITIVE LOGITS
    rainbow
    1.06
    occasion
    1.05
    uno
    1.04
     festive
    1.03
    ли
    1.01
    Overlap
    1.00
    opi
    0.99
    quint
    0.98
    estado
    0.98
    ch
    0.96
    Act Density 0.054%

    No Known Activations