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

    Neuronpedia

    INDEX
    Explanations

    working on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लोकांनी
    0.52
    ally
    0.48
    wenn
    0.44
    viene
    0.43
    fuel
    0.43
     மிக்க
    0.43
     використа
    0.42
    executed
    0.42
    oooo
    0.41
    workers
    0.41
    POSITIVE LOGITS
     projects
    0.68
     preparations
    0.67
     perfecting
    0.64
     preparing
    0.63
     proyecto
    0.61
     projets
    0.61
     progetti
    0.61
     proiect
    0.60
     projeto
    0.59
     prepara
    0.59
    Act Density 0.053%

    No Known Activations