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

    Neuronpedia

    INDEX
    Explanations

    say "201" numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пока
    -0.07
     GW
    -0.07
     tea
    -0.07
     seafood
    -0.07
    duction
    -0.07
     General
    -0.06
     kw
    -0.06
     hybrid
    -0.06
     пти
    -0.06
    TeV
    -0.06
    POSITIVE LOGITS
    سته
    0.07
     基
    0.06
     NavController
    0.06
     CRUD
    0.06
     أح
    0.06
    ΙΑΣ
    0.06
    xEC
    0.06
    .Split
    0.06
    ΕΠ
    0.06
     ενός
    0.06
    Act Density 0.062%

    No Known Activations