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

    Neuronpedia

    INDEX
    Explanations

    expired, cache, hist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.70
    ’
    0.64
    Input
    0.62
    ye
    0.61
    ي
    0.58
    io
    0.55
    ческий
    0.54
    orsion
    0.54
    5
    0.54
    ↵
    0.52
    POSITIVE LOGITS
     Indira
    0.63
     rekan
    0.62
     ura
    0.61
     foaf
    0.61
     beeswax
    0.60
     urgency
    0.59
    闓
    0.59
     코
    0.58
     coco
    0.58
     två
    0.58
    Act Density 0.000%

    No Known Activations