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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ex
    -0.07
     Ле
    -0.06
     leo
    -0.06
     hứ
    -0.06
    Anime
    -0.06
     Crafting
    -0.06
     �
    -0.06
    .VarChar
    -0.06
     Feature
    -0.06
    bar
    -0.06
    POSITIVE LOGITS
     transported
    0.07
     TRADE
    0.07
    errorMessage
    0.07
    uner
    0.07
    制作
    0.07
    构
    0.07
    -original
    0.07
     Tart
    0.07
    inan
    0.06
     agreeing
    0.06
    Act Density 0.014%

    No Known Activations