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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pods
    -0.07
     subtraction
    -0.07
    urn
    -0.07
    ‌شده
    -0.07
    Boy
    -0.07
     metal
    -0.06
     Tamil
    -0.06
     Arbitrary
    -0.06
     uppercase
    -0.06
     fruit
    -0.06
    POSITIVE LOGITS
     ingenious
    0.07
     кис
    0.07
     fortunately
    0.07
    (nome
    0.06
    [],
    0.06
    ffff
    0.06
     بط
    0.06
    flt
    0.06
     布
    0.06
    BeforeEach
    0.06
    Act Density 0.022%

    No Known Activations