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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensive
    -0.08
    ationToken
    -0.07
    ворю
    -0.07
    贝
    -0.07
    HEME
    -0.07
    _arguments
    -0.07
     oldValue
    -0.07
     accountId
    -0.07
    Reader
    -0.07
    控
    -0.06
    POSITIVE LOGITS
    diamond
    0.07
    (contact
    0.07
     مؤس
    0.07
    (helper
    0.07
     oauth
    0.06
    (mContext
    0.06
     bananas
    0.06
     haystack
    0.06
     direkt
    0.06
     inevitably
    0.06
    Act Density 0.001%

    No Known Activations