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

    Neuronpedia

    INDEX
    Explanations

    convert, translate, consider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poma
    0.43
     crusade
    0.41
    ポンプ
    0.41
     zašt
    0.40
     sağlar
    0.40
     undeniable
    0.39
     کجا
    0.38
    postcard
    0.38
     جز
    0.38
    کا
    0.38
    POSITIVE LOGITS
     prior
    0.43
    ለያዩ
    0.41
    >∕</
    0.41
     erg
    0.41
     পরে
    0.40
    采用了
    0.40
     displayNumber
    0.40
     spines
    0.39
     interfaces
    0.39
    使用了
    0.39
    Act Density 0.012%

    No Known Activations