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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     informed
    -0.07
     continents
    -0.06
    تأ
    -0.06
    _NAV
    -0.06
     vatandaş
    -0.06
    чреж
    -0.06
    /layouts
    -0.06
    찐
    -0.06
    진
    -0.06
     lstm
    -0.06
    POSITIVE LOGITS
    ∥
    0.08
     Lowest
    0.08
    ↥
    0.07
    .Rule
    0.07
     Toe
    0.07
     poly
    0.07
    威
    0.07
     Lex
    0.07
    (delay
    0.07
     ACCESS
    0.07
    Act Density 0.092%

    No Known Activations