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

    Neuronpedia

    INDEX
    Explanations

    knowing what is known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समझाया
    0.38
    浅
    0.36
    Pan
    0.35
     привы
    0.35
     spieg
    0.35
     समझा
    0.34
    Gloss
    0.34
    ᓂ
    0.34
    解説
    0.34
     boardwalk
    0.34
    POSITIVE LOGITS
     knowing
    1.86
     Knowing
    1.73
    知道
    1.73
     know
    1.72
     knew
    1.64
     knows
    1.63
    Knowing
    1.56
    knowing
    1.56
     mengetahui
    1.54
     biết
    1.52
    Act Density 0.037%

    No Known Activations