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

    Neuronpedia

    INDEX
    Explanations

    lists and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paid
    0.43
    غاية
    0.39
     हाँ
    0.39
     £
    0.39
    Fig
    0.38
    Please
    0.38
     (£
    0.37
    Struct
    0.37
     çıkarm
    0.37
     abbreviated
    0.37
    POSITIVE LOGITS
     පි
    0.40
     клеток
    0.38
    pSensor
    0.37
    oglu
    0.37
     আগুনে
    0.37
     шриф
    0.37
    мага
    0.37
     containers
    0.36
    ्रेडिट
    0.36
    ու
    0.36
    Act Density 0.000%

    No Known Activations