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

    Neuronpedia

    INDEX
    Explanations

    class or course context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যেমন
    0.50
     ちょっと
    0.49
     কমপ্লে
    0.47
     নিজেকে
    0.46
     delitos
    0.45
     args
    0.45
     déclare
    0.45
     táo
    0.44
     เงี้ย
    0.44
     politico
    0.43
    POSITIVE LOGITS
     as
    0.51
    یب
    0.50
    同期
    0.43
    as
    0.43
    ar
    0.43
    wick
    0.43
    ident
    0.42
    asmussen
    0.42
    syllabus
    0.41
    Similarity
    0.41
    Act Density 0.000%

    No Known Activations