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

    Neuronpedia

    INDEX
    Explanations

    animals/facts/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     какие
    0.43
    ってる
    0.40
    otri
    0.39
    膵
    0.39
    ώς
    0.38
     ilmiah
    0.37
    স্‌
    0.37
    阴
    0.37
     Biochemistry
    0.36
     описа
    0.36
    POSITIVE LOGITS
     USA
    0.41
     shop
    0.39
    sleep
    0.38
    USA
    0.38
     Bernad
    0.38
     relaxing
    0.37
     relax
    0.36
    कार्ट
    0.36
    ंडल
    0.35
     อัน
    0.35
    Act Density 0.000%

    No Known Activations