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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives followed by concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frühen
    0.69
     frü
    0.68
     delightfully
    0.67
     ต่าง
    0.64
     benda
    0.63
     comparatively
    0.63
     कृपया
    0.63
    ServiceInterface
    0.62
     배우
    0.61
     früheren
    0.61
    POSITIVE LOGITS
     Catalan
    0.88
     patrim
    0.85
     dimensión
    0.83
     vocation
    0.75
     parenthesis
    0.74
     patrimonio
    0.74
     rupture
    0.74
     nucleus
    0.73
     gastronomic
    0.73
     nuclei
    0.72
    Act Density 0.039%

    No Known Activations