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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detergent
    -0.07
     sembl
    -0.07
     comple
    -0.07
    怖
    -0.07
    牌
    -0.06
     jetzt
    -0.06
    ('./
    -0.06
    .inner
    -0.06
     worms
    -0.06
     stickers
    -0.06
    POSITIVE LOGITS
     outnumber
    0.07
    .core
    0.06
    Inicial
    0.06
    GE
    0.06
    ransition
    0.06
     loadImage
    0.06
     тов
    0.06
    andez
    0.06
    elerinden
    0.06
    serir
    0.06
    Act Density 0.069%

    No Known Activations