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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Free
    -0.06
     عالی
    -0.06
    :num
    -0.06
    <Q
    -0.06
     Biology
    -0.06
    #####
    -0.06
    (cli
    -0.06
     acclaimed
    -0.06
    -health
    -0.06
     zeal
    -0.06
    POSITIVE LOGITS
    (import
    0.06
     باید
    0.06
    .getParam
    0.06
     знаю
    0.06
     Vog
    0.06
    _sort
    0.06
    베
    0.06
    aic
    0.06
    不断
    0.06
    니아
    0.06
    Act Density 0.093%

    No Known Activations