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

    Neuronpedia

    INDEX
    Explanations

    demonstrate higher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Electronic
    0.53
    Sales
    0.47
    Những
    0.47
    Head
    0.46
    Operational
    0.46
    Editor
    0.46
    Design
    0.45
    Silver
    0.45
    Transportation
    0.45
    Office
    0.45
    POSITIVE LOGITS
    ри
    0.55
    р
    0.53
    penup
    0.50
     नित
    0.49
    rs
    0.49
    on
    0.49
    lag
    0.49
    lat
    0.48
    k
    0.48
     дети
    0.48
    Act Density 0.000%

    No Known Activations