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

    Neuronpedia

    INDEX
    Explanations

    skill and artistry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logique
    0.41
    Logical
    0.38
     analytical
    0.38
    ทร
    0.38
    逻辑
    0.37
     عربي
    0.37
    ເນ
    0.37
     lógica
    0.37
     świę
    0.37
    źdz
    0.37
    POSITIVE LOGITS
     skilled
    2.73
     skillful
    2.48
     skilful
    2.45
     Skilled
    2.36
    skilled
    2.27
     skill
    2.17
     Skill
    2.13
     skillfully
    2.11
     skil
    2.08
    skill
    1.99
    Act Density 0.029%

    No Known Activations