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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绑架
    -0.08
    刭
    -0.07
    Pressure
    -0.07
    archives
    -0.07
    缶
    -0.07
    DIFF
    -0.07
    .ReadString
    -0.07
     zaman
    -0.07
     jmp
    -0.06
    されて
    -0.06
    POSITIVE LOGITS
    +s
    0.06
    ASHBOARD
    0.06
    емых
    0.06
     שכ
    0.06
    执着
    0.06
     scrapy
    0.06
     Exhibit
    0.06
     lineup
    0.06
    expanded
    0.06
    款式
    0.06
    Act Density 0.000%

    No Known Activations