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

    Neuronpedia

    INDEX
    Explanations

    jargon, specialized, excellent, reveal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.94
     these
    0.93
     this
    0.93
    ,
    0.91
     an
    0.88
     the
    0.87
     that
    0.86
    hood
    0.85
     “
    0.84
     cognitive
    0.83
    POSITIVE LOGITS
    ཎ
    1.21
    Avg
    1.15
    ירים
    1.12
     Excelente
    1.12
    Accordion
    1.10
    Retry
    1.09
    quả
    1.09
    Edad
    1.09
    ఖ్య
    1.09
    ३
    1.09
    Act Density 0.464%

    No Known Activations