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

    Neuronpedia

    INDEX
    Explanations

    positive story appraisals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    1.43
     oder
    1.17
    或
    1.14
     или
    1.13
     أو
    1.11
     หรือ
    1.07
     또는
    1.05
    あるいは
    1.05
     अथवा
    1.04
     ou
    1.04
    POSITIVE LOGITS
     dzięki
    1.50
     grazie
    1.40
     díky
    1.35
     gracias
    1.30
     bardzo
    1.28
     praticamente
    1.23
     благодаря
    1.22
     rất
    1.20
    unlike
    1.19
     excelente
    1.19
    Act Density 1.154%

    No Known Activations