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

    Neuronpedia

    INDEX
    Explanations

    import PIL Image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Setter
    0.46
    midt
    0.41
    Tier
    0.40
     shifter
    0.40
    entering
    0.40
    邡
    0.40
    Swift
    0.39
     литератур
    0.39
    Reynolds
    0.39
    लान
    0.39
    POSITIVE LOGITS
     PIL
    1.18
    PIL
    1.05
     Image
    1.02
    Image
    0.99
     pil
    0.86
     image
    0.86
     Pillow
    0.83
     ImageTk
    0.77
    pil
    0.77
     pillow
    0.75
    Act Density 0.024%

    No Known Activations