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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    കരണ
    0.50
    Wallace
    0.48
     దర్శక
    0.46
     innym
    0.46
     방식으로
    0.46
    Named
    0.45
     formatter
    0.45
    arny
    0.45
     authorship
    0.44
    ‿
    0.44
    POSITIVE LOGITS
    leduj
    0.42
     Somalia
    0.41
    تاب
    0.40
    مر
    0.40
    جاب
    0.39
     ziemlich
    0.39
     guter
    0.39
    ظ
    0.39
    وا
    0.38
    wakeup
    0.38
    Act Density 0.012%

    No Known Activations