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

    Neuronpedia

    INDEX
    Explanations

    pronoun it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     których
    0.33
    원이
    0.32
    ifications
    0.32
    actionBarTab
    0.30
    ade
    0.30
    さを
    0.29
     שלה
    0.29
    od
    0.29
    लैंड
    0.29
    ران
    0.29
    POSITIVE LOGITS
    c
    0.40
     allemaal
    0.39
    inerary
    0.38
    俩
    0.36
    倆
    0.35
    льнай
    0.34
     habido
    0.32
     snowing
    0.32
    㗽
    0.32
     anhand
    0.31
    Act Density 0.085%

    No Known Activations