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

    Neuronpedia

    INDEX
    Explanations

    Random document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <std
    -0.07
    twenty
    -0.06
    _schema
    -0.06
    camp
    -0.06
     Quadr
    -0.06
     convex
    -0.06
    )...
    -0.06
     concent
    -0.06
     *"
    -0.06
     ersten
    -0.06
    POSITIVE LOGITS
    ompiler
    0.07
     أيض
    0.07
    uces
    0.07
    =
    0.07
     resc
    0.07
     Baba
    0.06
    ãi
    0.06
     sing
    0.06
    sta
    0.06
    _Address
    0.06
    Act Density 0.000%

    No Known Activations