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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rss
    -0.07
    mps
    -0.07
    保湿
    -0.07
     ech
    -0.07
     createDate
    -0.07
    strcpy
    -0.07
     licence
    -0.07
    atee
    -0.07
    (dead
    -0.07
     cov
    -0.06
    POSITIVE LOGITS
    edi
    0.07
     preceded
    0.07
    Memo
    0.07
    /f
    0.06
    _REF
    0.06
    红楼
    0.06
    -helper
    0.06
    apid
    0.06
    wyż
    0.06
    filters
    0.06
    Act Density 0.035%

    No Known Activations