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

    Neuronpedia

    INDEX
    Explanations

    sensory information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    球迷
    0.47
     muốn
    0.42
    ခြ
    0.41
     বাগান
    0.41
    董事长
    0.40
    叁章
    0.39
     ಕಿ
    0.39
    楼主
    0.39
    ﺝ
    0.39
     chcete
    0.38
    POSITIVE LOGITS
    s
    0.48
    Libraries
    0.43
    Reserved
    0.42
    EMT
    0.41
    wide
    0.41
    Startup
    0.40
    freund
    0.40
    厦
    0.40
     reserved
    0.39
    able
    0.39
    Act Density 0.000%

    No Known Activations