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

    Neuronpedia

    INDEX
    Explanations

    time delays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Camp
    -0.07
     Valerie
    -0.07
    (DATA
    -0.06
     diabetes
    -0.06
     Malk
    -0.06
     Matthias
    -0.06
     Scoped
    -0.06
    trade
    -0.06
     fetched
    -0.06
    偷
    -0.06
    POSITIVE LOGITS
    :string
    0.07
    ção
    0.07
     DisplayName
    0.07
     repeat
    0.06
    ोट
    0.06
     anos
    0.06
    .ObjectMeta
    0.06
    치
    0.06
    اون
    0.06
    сть
    0.06
    Act Density 0.014%

    No Known Activations