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

    Neuronpedia

    INDEX
    Explanations

    explaining why or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    detailed
    0.34
     повседнев
    0.30
    積極的に
    0.30
    詳細は
    0.30
    ସ୍
    0.30
    fact
    0.29
    ೈ
    0.29
    ভগ
    0.29
     সময়ের
    0.29
     توانید
    0.29
    POSITIVE LOGITS
     mengapa
    0.41
     first
    0.40
     först
    0.40
     sytuacji
    0.39
     dulu
    0.38
     først
    0.38
     terlebih
    0.37
     why
    0.37
     پہلے
    0.37
     aici
    0.37
    Act Density 0.003%

    No Known Activations