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

    Neuronpedia

    INDEX
    Explanations

    urls with domains like .org and .com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.70
     is
    0.66
     a
    0.65
    ning
    0.63
    دون
    0.62
     to
    0.58
    ны
    0.58
    లు
    0.58
    s
    0.58
    ttes
    0.55
    POSITIVE LOGITS
    ید
    0.89
    P
    0.81
    ने
    0.80
    D
    0.80
     gode
    0.75
    फारिश
    0.75
     destek
    0.74
    izamos
    0.73
    R
    0.70
    р
    0.68
    Act Density 0.132%

    No Known Activations