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

    Neuronpedia

    INDEX
    Explanations

    sky is blue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.84
    e
    0.74
    ,
    0.71
     $
    0.66
    ys
    0.66
    s
    0.66
    f
    0.63
    p
    0.62
     >
    0.59
     <
    0.59
    POSITIVE LOGITS
    ку
    0.62
     ಮೋ
    0.61
    𝗻
    0.61
     ಖರೀ
    0.61
    ຜະລິດຕ
    0.60
    ید
    0.59
    OSED
    0.58
    ке
    0.57
     মনীষ
    0.56
    メディア
    0.55
    Act Density 0.125%

    No Known Activations