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

    Neuronpedia

    INDEX
    Explanations

    sieve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lau
    -0.08
    _ENTRY
    -0.07
    Unmarshaller
    -0.07
    Hel
    -0.07
    玄
    -0.07
    但却
    -0.07
    喜剧
    -0.07
    maries
    -0.07
    _MED
    -0.07
    从来没有
    -0.07
    POSITIVE LOGITS
    טיב
    0.07
    蔈
    0.07
     gv
    0.07
     SEO
    0.07
     saber
    0.07
    התנגד
    0.06
     pprint
    0.06
    샾
    0.06
    pageSize
    0.06
    :pointer
    0.06
    Act Density 0.003%

    No Known Activations