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

    Neuronpedia

    INDEX
    Explanations

    programming code and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amma
    0.37
     ১৪
    0.37
     буты
    0.36
    }^{-}\
    0.35
     каждый
    0.35
    ที่ไม่
    0.35
     Pedagog
    0.35
    EntryPoint
    0.35
    Exporter
    0.35
    beatCounter
    0.35
    POSITIVE LOGITS
    ierre
    0.36
    queue
    0.33
     kelu
    0.33
     relayed
    0.33
     ods
    0.32
     ease
    0.32
    先
    0.32
    bs
    0.32
     uph
    0.32
    ooq
    0.32
    Act Density 0.002%

    No Known Activations