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

    Neuronpedia

    INDEX
    Explanations

    complex questions and debates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avulla
    0.44
     streamlined
    0.42
     modular
    0.41
     framebuffer
    0.40
    साना
    0.40
     använder
    0.39
     Lucky
    0.39
     স্ম
    0.38
     использовать
    0.38
     hochwertige
    0.38
    POSITIVE LOGITS
     debated
    1.14
     debate
    1.08
     debates
    1.04
    争议
    1.00
     controversy
    0.99
     débat
    0.99
    debate
    0.95
     controversies
    0.95
     debatable
    0.91
     debating
    0.91
    Act Density 0.434%

    No Known Activations