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

    Neuronpedia

    INDEX
    Explanations

    practical effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.48
    example
    0.43
    because
    0.42
    Foundation
    0.41
    Indonesia
    0.41
    у
    0.41
    因为
    0.41
    University
    0.41
    2
    0.40
    constitutional
    0.40
    POSITIVE LOGITS
     ontwerp
    0.48
     caf
    0.48
     landscaped
    0.47
    addGroup
    0.45
    দেশীয়
    0.45
    leton
    0.45
     kró
    0.44
     variedades
    0.44
     அடையாளம்
    0.44
     collectionView
    0.43
    Act Density 0.002%

    No Known Activations