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

    Neuronpedia

    INDEX
    Explanations

    pair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Advice
    -0.07
     Planning
    -0.07
    REV
    -0.06
    Character
    -0.06
     switching
    -0.06
     Porto
    -0.06
     fileType
    -0.06
    What
    -0.06
    scopy
    -0.06
    Priority
    -0.06
    POSITIVE LOGITS
     går
    0.07
     pInfo
    0.07
    ................
    0.07
     artworks
    0.06
     OnePlus
    0.06
     กร
    0.06
    -pack
    0.06
    /start
    0.06
     ช
    0.06
     azi
    0.06
    Act Density 0.006%

    No Known Activations