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

    Neuronpedia

    INDEX
    Explanations

    update, intertwined, effective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zdjęcia
    0.47
     استخدام
    0.42
    公元
    0.40
     kulland
    0.40
     useRouter
    0.39
     جبر
    0.39
    गुर
    0.39
     Dresden
    0.38
    చిత
    0.38
     사용자
    0.37
    POSITIVE LOGITS
     perju
    0.47
    icios
    0.41
    okk
    0.41
     Continuando
    0.37
    hei
    0.36
    inaldo
    0.36
    iffs
    0.35
    arrive
    0.35
     buổi
    0.35
    icio
    0.34
    Act Density 0.000%

    No Known Activations