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

    Neuronpedia

    INDEX
    Explanations

    lack of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embeddings
    0.66
     subordinates
    0.59
     streamline
    0.58
    ঠিত
    0.58
    事业
    0.56
    眯
    0.56
     raster
    0.55
    SIX
    0.55
    latitude
    0.54
    ntag
    0.54
    POSITIVE LOGITS
    д
    0.57
    at
    0.53
    ı
    0.52
     Kaffee
    0.48
     dimiliki
    0.48
     esperti
    0.48
    หร่
    0.47
    {
    0.47
    ingen
    0.47
     esimerkiksi
    0.46
    Act Density 0.049%

    No Known Activations