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

    Neuronpedia

    INDEX
    Explanations

    structured lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这
    0.39
    这个
    0.36
     همچنین
    0.34
    這
    0.34
     ซึ่ง
    0.34
     যদি
    0.33
    這個
    0.33
     که
    0.31
     that
    0.31
    この
    0.31
    POSITIVE LOGITS
     통한
    0.33
     difficult
    0.33
     unsustainable
    0.32
     relatable
    0.30
     used
    0.29
     위한
    0.29
     stressful
    0.29
     인한
    0.29
     primeiras
    0.29
     traumatic
    0.28
    Act Density 1.807%

    No Known Activations