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

    Neuronpedia

    INDEX
    Explanations

    animal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.45
     unsatisfactory
    0.35
    भिन्न
    0.34
     of
    0.33
    the
    0.31
    änd
    0.30
    ceived
    0.30
    indeed
    0.29
    sentences
    0.29
    jiwarl
    0.29
    POSITIVE LOGITS
    だったので
    0.36
    之旅
    0.36
    ﺯ
    0.31
     alebo
    0.30
     দিয়েছিল
    0.30
     или
    0.29
     WITHOUT
    0.29
     কিংবা
    0.29
     Primavera
    0.29
     maroc
    0.29
    Act Density 0.255%

    No Known Activations