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

    Neuronpedia

    INDEX
    Explanations

    connectors and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     দেখিয়
    0.46
    ளான
    0.41
     eminently
    0.41
     লাগিলেন
    0.41
     মনুষ
    0.41
     কতকগুলি
    0.41
    hypoth
    0.40
    高考
    0.40
     তাহাতে
    0.40
    ד
    0.40
    POSITIVE LOGITS
    ・
    0.46
    และ
    0.44
    -
    0.44
     এবং
    0.42
     किंवा
    0.42
    نز
    0.41
     and
    0.40
     و
    0.40
     veya
    0.40
     initial
    0.40
    Act Density 0.010%

    No Known Activations