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

    Neuronpedia

    INDEX
    Explanations

    price ranges and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ко
    1.58
    அல்ல
    1.41
    बॉलीवुड
    1.39
    चलिए
    1.37
    मध्यप्रदेश
    1.35
    да
    1.34
    नमस्कार
    1.34
    𝐭
    1.31
     войск
    1.29
    तुम्हारा
    1.28
    POSITIVE LOGITS
    ell
    1.43
    有很多
    1.34
    urile
    1.31
    1.30
    aceut
    1.30
     trente
    1.30
    的な
    1.27
     scler
    1.26
     الا
    1.23
    し
    1.23
    Act Density 0.033%

    No Known Activations