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

    Neuronpedia

    INDEX
    Explanations

    pronoun followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    この
    0.39
    il
    0.38
    știg
    0.38
    ují
    0.38
     an
    0.38
    いっぱい
    0.38
     المعاد
    0.37
    마
    0.37
     Không
    0.36
    Этот
    0.36
    POSITIVE LOGITS
     usages
    0.35
     vou
    0.34
     apprezz
    0.34
    soever
    0.33
     dvs
    0.32
    ™.
    0.31
     khususnya
    0.30
     mids
    0.30
     audiences
    0.29
     ಹಾಗೂ
    0.29
    Act Density 0.025%

    No Known Activations