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

    Neuronpedia

    INDEX
    Explanations

    product or technical name components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ধরে
    0.34
     অভাবে
    0.28
     হাত
    0.27
    Runnable
    0.27
     Schum
    0.27
    তবে
    0.27
     বছর
    0.27
    ায়ী
    0.27
     asker
    0.27
    ểu
    0.26
    POSITIVE LOGITS
    ،
    0.37
     maupun
    0.32
    ّى
    0.31
    ™,
    0.30
    那种
    0.29
    <0xD8>
    0.29
     undeniably
    0.29
    യ്യ
    0.29
    와
    0.29
     همچنین
    0.28
    Act Density 0.372%

    No Known Activations