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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bell
    -0.08
     retali
    -0.08
     instructions
    -0.08
     підт
    -0.08
     admon
    -0.08
     sophisticated
    -0.08
     reprim
    -0.08
     Wayne
    -0.08
     ті
    -0.07
     replen
    -0.07
    POSITIVE LOGITS
     താര
    0.12
     തമ്മ
    0.10
     срав
    0.10
     بينها
    0.10
     비교
    0.10
     comparison
    0.09
    比较
    0.09
     hinsichtlich
    0.09
    ('',
    0.09
    Compare
    0.09
    Act Density 0.025%

    No Known Activations