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

    Neuronpedia

    INDEX
    Explanations

    go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     일본
    -0.07
     리스트
    -0.07
     shut
    -0.07
     cut
    -0.07
    .For
    -0.06
    bx
    -0.06
     lazy
    -0.06
    ({});↵
    -0.06
    りと
    -0.06
     Patient
    -0.06
    POSITIVE LOGITS
    全球
    0.07
     alış
    0.06
    ۱۹۴
    0.06
     stringBuffer
    0.06
     trộn
    0.06
    imageView
    0.06
     мої
    0.06
    십
    0.06
    _Float
    0.06
    στρο
    0.06
    Act Density 0.004%

    No Known Activations