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

    Neuronpedia

    INDEX
    Explanations

    demonstratives implying specificity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    force
    0.34
    att
    0.31
     and
    0.30
    with
    0.30
    part
    0.29
    pro
    0.28
    intage
    0.28
    both
    0.28
     with
    0.28
    port
    0.28
    POSITIVE LOGITS
     particulares
    0.42
     particuliers
    0.39
     특정
    0.39
     particulier
    0.38
    िकुलर
    0.35
     particular
    0.35
     suatu
    0.35
     उक्त
    0.35
     কাজটি
    0.35
     해당
    0.33
    Act Density 0.023%

    No Known Activations