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

    Neuronpedia

    INDEX
    Explanations

    no use, were playing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.43
    ዳ
    1.34
    ı
    1.31
     digress
    1.30
    wallet
    1.29
    idea
    1.28
    perfect
    1.27
    ี
    1.26
    其中包括
    1.26
    সর্ব
    1.25
    POSITIVE LOGITS
    𝒶
    1.54
    𝓊
    1.49
    a
    1.42
    𝓉
    1.35
    বীন্দ্রনাথ
    1.35
    ようになる
    1.30
    𝓈
    1.27
     multipart
    1.26
    Chorus
    1.24
    borderRadius
    1.23
    Act Density 0.000%

    No Known Activations