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

    Neuronpedia

    INDEX
    Explanations

    gemma, widely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이에요
    0.31
    ించి
    0.27
     التى
    0.27
    thisStudent
    0.26
    出现了
    0.26
    আছে
    0.26
     있으며
    0.26
    했고
    0.26
    ทาน
    0.26
    用い
    0.26
    POSITIVE LOGITS
     refrained
    0.37
     realize
    0.35
     realized
    0.35
     don
    0.31
    ament
    0.29
     realizes
    0.29
     never
    0.29
     estado
    0.27
     wszystko
    0.27
     will
    0.27
    Act Density 5.155%

    No Known Activations