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

    Neuronpedia

    INDEX
    Explanations

    13B models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.52
    ین
    0.45
    ებელი
    0.45
     рішення
    0.45
    编辑
    0.44
     adultos
    0.43
     करके
    0.43
    り
    0.42
     estágio
    0.42
    があ
    0.42
    POSITIVE LOGITS
     Иванов
    0.50
    azam
    0.50
     thirteen
    0.49
    arent
    0.48
     Thirteen
    0.47
     wre
    0.45
     VO
    0.45
    一带
    0.45
     IOC
    0.44
     loob
    0.44
    Act Density 0.250%

    No Known Activations