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

    Neuronpedia

    INDEX
    Explanations

    learning and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apartamentos
    0.35
     selecciona
    0.35
    aktionen
    0.35
    ke
    0.33
    ley
    0.33
    isions
    0.33
    ena
    0.31
    icycles
    0.31
    LEY
    0.31
     permitem
    0.31
    POSITIVE LOGITS
     skills
    0.82
     Skills
    0.79
     aprender
    0.71
     навыки
    0.71
    Skills
    0.70
     learn
    0.68
    學習
    0.67
    skills
    0.65
     تعلم
    0.65
     learning
    0.63
    Act Density 0.694%

    No Known Activations