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

    Neuronpedia

    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اقة
    -0.07
    еров
    -0.07
    Containers
    -0.07
     lump
    -0.06
     ideally
    -0.06
     terminal
    -0.06
    내
    -0.06
    xeb
    -0.06
    그러
    -0.06
    िप
    -0.06
    POSITIVE LOGITS
     Deer
    0.07
     Twin
    0.07
     fights
    0.07
    (payload
    0.07
     Duch
    0.06
     photographer
    0.06
    Traffic
    0.06
     useEffect
    0.06
     ::=
    0.06
    (lang
    0.06
    Act Density 0.013%

    No Known Activations