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

    Neuronpedia

    INDEX
    Explanations

    multilingual conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    1.36
    ième
    1.34
    :<
    1.33
    :
    1.30
    ies
    1.29
    en
    1.25
    ä
    1.24
     cortex
    1.23
    ة
    1.20
    回事
    1.17
    POSITIVE LOGITS
     ו
    1.55
     अन्य
    1.46
     על
    1.38
     ಹಾಗೂ
    1.37
     ఇతర
    1.34
     שה
    1.33
     और
    1.32
     त्यस
    1.31
     و
    1.30
     في
    1.29
    Act Density 1.722%

    No Known Activations