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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यूनिट
    0.48
    ್ರೆ
    0.47
    客户
    0.46
     onboarding
    0.46
    <0x1D>
    0.46
     müşteri
    0.46
     voltaje
    0.45
     soude
    0.45
     గేమ్
    0.45
    商家
    0.44
    POSITIVE LOGITS
     Wikipedia
    1.08
     Wikimedia
    1.05
     Wikiped
    0.96
    Wikipedia
    0.95
     wikipedia
    0.93
     wiki
    0.88
    Wikimedia
    0.85
     Wiki
    0.83
     Вики
    0.82
    wikipedia
    0.81
    Act Density 0.027%

    No Known Activations