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

    Neuronpedia

    INDEX
    Explanations

    driven by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    騇
    0.50
     menilai
    0.45
     defam
    0.43
     അറിയ
    0.42
    涹
    0.42
     אחר
    0.42
    ="";
    0.41
    随机
    0.41
     announcements
    0.41
    editText
    0.40
    POSITIVE LOGITS
     Von
    0.49
     sacrifice
    0.46
     US
    0.45
     cette
    0.45
     Lewis
    0.45
     tubular
    0.44
     व्यू
    0.44
     chord
    0.44
     sold
    0.43
     missionary
    0.43
    Act Density 0.005%

    No Known Activations