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

    Neuronpedia

    INDEX
    Explanations

    did, id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     являются
    -0.07
     لأن
    -0.07
    /#
    -0.07
     微
    -0.06
    _par
    -0.06
    ulant
    -0.06
    Genres
    -0.06
     منه
    -0.06
     universal
    -0.06
     Nguyen
    -0.06
    POSITIVE LOGITS
    ед
    0.07
    .makeText
    0.06
    IFT
    0.06
    edia
    0.06
    QUIRE
    0.06
    REG
    0.06
     плеч
    0.06
    -ed
    0.06
    GA
    0.06
    alu
    0.06
    Act Density 0.025%

    No Known Activations