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

    Neuronpedia

    INDEX
    Explanations

    bet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لام
    -0.08
     CFR
    -0.07
    rain
    -0.07
     Forever
    -0.07
     uzman
    -0.06
    AREA
    -0.06
     Innovation
    -0.06
    modules
    -0.06
    πτυ
    -0.06
    عار
    -0.06
    POSITIVE LOGITS
     harsh
    0.07
     ro
    0.06
    /ng
    0.06
    /pi
    0.06
     residence
    0.06
    کز
    0.06
    &&(
    0.06
    *ft
    0.06
    (property
    0.06
    Terminate
    0.06
    Act Density 0.013%

    No Known Activations