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
     Colon
    -0.07
     SUB
    -0.06
     Amazon
    -0.06
     drills
    -0.06
    éry
    -0.06
    [X
    -0.06
    Mad
    -0.06
     Кост
    -0.06
    itary
    -0.06
    Healthy
    -0.06
    POSITIVE LOGITS
    .Override
    0.07
     آنها
    0.06
     sĩ
    0.06
    textarea
    0.06
    ัฒนา
    0.06
    	o
    0.06
     futbol
    0.06
    اوه
    0.06
    زاده
    0.06
     mientras
    0.06
    Act Density 0.013%

    No Known Activations