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

    Neuronpedia

    INDEX
    Explanations

    pronouns they/them/it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.67
    ↵
    0.63
     can
    0.58
     are
    0.52
    ,
    0.49
    </h3>
    0.49
     road
    0.46
     COVID
    0.45
    ও
    0.45
     o
    0.45
    POSITIVE LOGITS
     ذریع
    0.55
    akaranam
    0.49
    with
    0.48
    調節
    0.47
    тись
    0.47
    that
    0.46
    尒
    0.46
     متعلقه
    0.46
    atthena
    0.45
    recyclerView
    0.45
    Act Density 0.193%

    No Known Activations