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

    Neuronpedia

    INDEX
    Explanations

    fact-checking. URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    भोपाल
    0.37
     Rhoda
    0.36
    isHidden
    0.35
     StatefulWidget
    0.35
    ネート
    0.33
    HttpHeaders
    0.33
    وك
    0.33
    BUCK
    0.33
     సంవ
    0.33
     setCurrent
    0.33
    POSITIVE LOGITS
     hele
    0.42
     ауто
    0.41
     rezult
    0.39
     x
    0.38
     regeneration
    0.38
     woo
    0.38
     keluar
    0.38
     reg
    0.38
     ziua
    0.37
    ux
    0.37
    Act Density 0.001%

    No Known Activations