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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essence
    -0.07
    咋
    -0.07
     Kind
    -0.07
     dataSource
    -0.07
    Vo
    -0.07
     projector
    -0.07
     Soup
    -0.07
     sovere
    -0.07
    .toBe
    -0.06
    Must
    -0.06
    POSITIVE LOGITS
     evasion
    0.07
    ENCED
    0.06
    ᆞ
    0.06
    家乡
    0.06
    すぎる
    0.06
    地标
    0.06
    CategoryId
    0.06
    的各项
    0.06
     đạt
    0.06
    picked
    0.06
    Act Density 0.001%

    No Known Activations