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

    Neuronpedia

    INDEX
    Explanations

    academic writings and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tranquilidad
    0.53
     आसान
    0.53
     emocionante
    0.52
     przyjem
    0.52
     errand
    0.52
     pipette
    0.52
     fácil
    0.51
     chcia
    0.50
     yummy
    0.50
     whopping
    0.49
    POSITIVE LOGITS
     writings
    1.21
     scholarly
    1.21
     literature
    1.20
     publications
    1.20
     literatura
    1.08
    literature
    1.07
     treatises
    1.05
    文献
    1.04
    publications
    1.02
     discussions
    1.02
    Act Density 0.746%

    No Known Activations