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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buses
    -0.06
     Trades
    -0.06
     bump
    -0.06
     employee
    -0.06
    주소
    -0.06
     Weiter
    -0.06
     blurry
    -0.06
    Illustr
    -0.06
     �
    -0.06
    -random
    -0.06
    POSITIVE LOGITS
    ava
    0.06
    氧
    0.06
     conceive
    0.06
    :min
    0.06
    ate
    0.06
     zal
    0.06
     (*)(
    0.06
    tearDown
    0.06
     experiencia
    0.06
    aniem
    0.06
    Act Density 0.199%

    No Known Activations