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

    Neuronpedia

    INDEX
    Explanations

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebelah
    1.05
    en
    0.98
    த்
    0.87
    ாமல்
    0.86
     نفر
    0.82
    ोत्तर
    0.79
    strictly
    0.78
     शुभकामनाएं
    0.78
    何を
    0.78
     Rxe
    0.78
    POSITIVE LOGITS
    一来
    1.21
     as
    1.16
    ंबई
    1.12
     например
    1.12
    𝙇
    1.11
    ेडकर
    1.09
     вот
    1.07
    𝙏
    1.06
    izophren
    1.06
    ôtels
    1.05
    Act Density 0.026%

    No Known Activations