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

    Neuronpedia

    INDEX
    Explanations

    swift

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .grpc
    -0.07
    引起的
    -0.07
    生产经营
    -0.07
    ㎏
    -0.07
     teil
    -0.07
    (Filter
    -0.07
    עם
    -0.07
    A
    -0.07
     sobie
    -0.07
     nasıl
    -0.07
    POSITIVE LOGITS
    宽度
    0.07
    .Pop
    0.07
     emph
    0.07
    Helmet
    0.06
    irm
    0.06
    uture
    0.06
     crossover
    0.06
    criptor
    0.06
     prototype
    0.06
    듷
    0.06
    Act Density 0.002%

    No Known Activations