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

    Neuronpedia

    INDEX
    Explanations

    structures, keys, and group names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cookware
    1.37
     furious
    1.18
    ี
    1.16
     captivated
    1.16
     enraged
    1.13
    irected
    1.11
     glamorous
    1.11
    غة
    1.10
    壌
    1.10
     loot
    1.10
    POSITIVE LOGITS
    рте
    1.33
    𝐺
    1.29
    𝑣
    1.19
    𝑢
    1.18
    𝑘
    1.16
    𝑈
    1.15
     границы
    1.06
    𝑀
    1.04
    𝜇
    1.03
    𝐻
    1.02
    Act Density 0.004%

    No Known Activations