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

    Neuronpedia

    INDEX
    Explanations

    JavaScript runtime environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بل
    0.49
     źród
    0.48
    ꯑ
    0.48
     indef
    0.46
    測定
    0.46
    防
    0.46
    اين
    0.44
     hyperplane
    0.44
    adoff
    0.44
    ação
    0.44
    POSITIVE LOGITS
    Bev
    0.67
    KEN
    0.60
     Bev
    0.60
     Stew
    0.59
     Dee
    0.58
    TE
    0.57
    ТЕ
    0.57
     berdoa
    0.56
     TE
    0.55
     you
    0.55
    Act Density 0.011%

    No Known Activations