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

    Neuronpedia

    INDEX
    Explanations

    examples and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    (fil
    -0.07
    호
    -0.07
     Definitely
    -0.07
    조건
    -0.07
    ileen
    -0.07
     userRepository
    -0.07
    פייס
    -0.07
     실제로
    -0.07
    脓
    -0.07
    POSITIVE LOGITS
    été
    0.09
     casc
    0.08
    普惠
    0.07
     cascade
    0.07
     transformative
    0.07
    _shortcode
    0.07
    ータ
    0.06
    รวม
    0.06
    0.06
    ISODE
    0.06
    Act Density 0.468%

    No Known Activations