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

    Neuronpedia

    INDEX
    Explanations

    unit or shame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eğer
    0.54
     anty
    0.49
     parking
    0.47
     artery
    0.45
    단
    0.45
     jeśli
    0.45
    丽
    0.45
     estén
    0.44
     yıld
    0.43
    אם
    0.43
    POSITIVE LOGITS
    शीलता
    0.50
     Natives
    0.46
    ιο
    0.45
    рів
    0.45
     Rim
    0.44
     Mainland
    0.44
    ството
    0.44
    த்திற்க
    0.43
    emans
    0.43
    žal
    0.42
    Act Density 0.000%

    No Known Activations