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

    Neuronpedia

    INDEX
    Explanations

    algebraic structures and mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уверен
    0.78
     incroyable
    0.75
    予測
    0.73
    迅速
    0.72
     increíble
    0.71
    acheteur
    0.71
    持續
    0.70
    appré
    0.68
    нимание
    0.68
     невероят
    0.68
    POSITIVE LOGITS
     morphisms
    1.17
     algebras
    1.05
     automorphisms
    1.05
     finitely
    1.03
     automorphism
    1.02
     isomorphism
    1.01
     polynomials
    1.00
     profinite
    1.00
     subalgebras
    0.97
     morphism
    0.96
    Act Density 0.000%

    No Known Activations