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

    Neuronpedia

    INDEX
    Explanations

    demonstrate software, ensuring fairness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erate
    0.52
    in
    0.47
    ة
    0.46
     continue
    0.46
     Libertad
    0.46
     reproduce
    0.46
    idencia
    0.45
    ar
    0.45
     facilitate
    0.45
    Mater
    0.44
    POSITIVE LOGITS
    currentSprite
    0.46
     оюндары
    0.45
    蝇
    0.45
     intégral
    0.45
    README
    0.44
    чёт
    0.43
    สร
    0.43
     ponctuées
    0.43
     sepatu
    0.42
     beserta
    0.42
    Act Density 0.003%

    No Known Activations