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

    Neuronpedia

    INDEX
    Explanations

    working together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    与其他
    0.58
     Various
    0.46
     각종
    0.44
    Various
    0.43
     এসব
    0.41
     चारों
    0.41
    各种
    0.39
     बाहेर
    0.39
    หลากหลาย
    0.39
     ငါ
    0.38
    POSITIVE LOGITS
     intertwined
    1.02
     coexist
    1.01
     begge
    1.00
     juntos
    0.99
     mutually
    0.96
     complementary
    0.95
     beiden
    0.93
     together
    0.92
     서로
    0.90
     keduanya
    0.90
    Act Density 0.079%

    No Known Activations