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

    Neuronpedia

    INDEX
    Explanations

    under specific circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alakip
    1.79
    yczne
    1.69
    yczny
    1.65
    avacak
    1.61
    oelectric
    1.56
    apeake
    1.53
    iverr
    1.53
    szág
    1.52
    ត្
    1.49
     trak
    1.49
    POSITIVE LOGITS
    Er
    1.61
    Illuminate
    1.53
    UNG
    1.49
    ung
    1.43
    世話
    1.41
     المز
    1.31
    Ẻ
    1.29
    UN
    1.28
    Mil
    1.27
    ਾਂ
    1.26
    Act Density 0.094%

    No Known Activations