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

    Neuronpedia

    INDEX
    Explanations

    Nihilism, NiFi, Niue, NIA, Nijisanji, Niqab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மற்றொரு
    0.45
    餑
    0.44
     Dados
    0.41
    ປະກອບ
    0.41
     ANOTHER
    0.39
    岦
    0.39
    another
    0.39
     another
    0.38
    श्रेष्ठ
    0.38
    另一个
    0.38
    POSITIVE LOGITS
     نی
    0.63
     니
    0.56
     ní
    0.52
     Ні
    0.51
     நி
    0.50
     ニ
    0.50
     Ni
    0.50
     nir
    0.50
    ニ
    0.49
     Ни
    0.48
    Act Density 0.021%

    No Known Activations