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

    Neuronpedia

    INDEX
    Explanations

    security cameras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Undang
    0.53
    unda
    0.49
    und
    0.48
    牪
    0.47
     Deity
    0.46
    ed
    0.46
    یشه
    0.45
     listopadu
    0.45
    едера
    0.44
    нього
    0.44
    POSITIVE LOGITS
    buttonclick
    0.43
     dispenser
    0.42
     guacamole
    0.42
     chloro
    0.41
    ức
    0.40
    ImageFilter
    0.40
    Resistance
    0.39
     caramel
    0.39
     প্রতিরোধ
    0.39
     protéger
    0.39
    Act Density 0.000%

    No Known Activations