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

    Neuronpedia

    INDEX
    Explanations

    "I" followed by "fits" or "Red"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arc
    0.39
    diet
    0.38
    дые
    0.38
    ネット
    0.37
    arc
    0.37
    сына
    0.35
     basketball
    0.34
    oyle
    0.34
    ំនួន
    0.34
    食
    0.34
    POSITIVE LOGITS
    GTUIKit
    0.43
    ၀
    0.41
     Authentic
    0.41
     strconv
    0.39
     Sesam
    0.39
    Authent
    0.39
     Meanwhile
    0.38
     gamanam
    0.38
     الاجتما
    0.38
    ลล์
    0.37
    Act Density 0.002%

    No Known Activations