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

    Neuronpedia

    INDEX
    Explanations

    s light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ystems
    0.83
    ys
    0.75
    acola
    0.70
    atuan
    0.67
     youngest
    0.67
    icherheit
    0.66
    ource
    0.66
     alkalmaz
    0.65
    ystem
    0.65
    ensitivity
    0.64
    POSITIVE LOGITS
    Light
    0.91
    PRESSED
    0.82
    ПР
    0.80
     Light
    0.79
    light
    0.79
    знача
    0.78
    LIGHT
    0.78
    лег
    0.78
    šti
    0.77
    Rep
    0.77
    Act Density 0.019%

    No Known Activations