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

    Neuronpedia

    INDEX
    Explanations

    RAINN URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rover
    0.78
    Ros
    0.73
     ros
    0.67
     Ros
    0.66
    跌
    0.65
     نضيف
    0.65
    stitch
    0.65
     rover
    0.65
    受注
    0.65
    utdown
    0.64
    POSITIVE LOGITS
     Ring
    0.83
    Ring
    0.79
     ring
    0.72
    ΠΟ
    0.67
     RING
    0.64
    Tin
    0.64
     Tin
    0.62
    ring
    0.62
     Kapol
    0.62
    쳐
    0.60
    Act Density 0.005%

    No Known Activations