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
     tastes
    -0.07
    added
    -0.07
     Seat
    -0.07
    .fixed
    -0.07
    stri
    -0.07
    /info
    -0.06
     prestigious
    -0.06
     preserved
    -0.06
     collecting
    -0.06
     TER
    -0.06
    POSITIVE LOGITS
    로나
    0.07
     Alg
    0.07
     benefici
    0.06
     adjustments
    0.06
    _UNKNOWN
    0.06
     віднов
    0.06
     sürekli
    0.06
     nev
    0.06
    (blank
    0.06
    RELATED
    0.06
    Act Density 0.002%

    No Known Activations