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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tbl
    -0.07
    ':['
    -0.07
    .bottom
    -0.07
     사
    -0.07
    mploy
    -0.06
     twig
    -0.06
     analysed
    -0.06
    학기
    -0.06
    xae
    -0.06
    .getDay
    -0.06
    POSITIVE LOGITS
    وف
    0.07
    そして
    0.07
     그렇
    0.07
    聲
    0.07
    Desc
    0.06
    ATURE
    0.06
    
    0.06
    Quotes
    0.06
    Greek
    0.06
    ②
    0.06
    Act Density 0.005%

    No Known Activations