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

    Neuronpedia

    INDEX
    Explanations

    rates and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.32
     Щ
    0.32
    ik
    0.30
    ون
    0.30
    ంథ
    0.29
    ის
    0.28
     använda
    0.28
    ന്ഥ
    0.28
     ഏത
    0.28
     സുമിത്ര
    0.27
    POSITIVE LOGITS
    。《
    0.39
    ।
    0.37
    。
    0.33
    。『
    0.31
    ۔
    0.31
    t
    0.30
    。「
    0.29
    ។
    0.29
    d
    0.28
    𝘨
    0.28
    Act Density 0.149%

    No Known Activations