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

    Neuronpedia

    INDEX
    Explanations

    detailed quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ం
    1.41
    이자
    1.30
    ้
    1.29
    ς
    1.22
     postulate
    1.14
     जाहिर
    1.13
    katore
    1.13
     mö
    1.13
    assadors
    1.13
    hashMap
    1.13
    POSITIVE LOGITS
    ش
    1.43
    IN
    1.29
    та
    1.26
    它
    1.26
    ТА
    1.22
    瓏
    1.18
    獃
    1.16
    鸠
    1.15
    то
    1.14
    口感
    1.14
    Act Density 0.256%

    No Known Activations