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

    Neuronpedia

    INDEX
    Explanations

    factoring, education, flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thisStudent
    0.43
    テーマ
    0.38
     quests
    0.37
    フィ
    0.37
     ಕೆಲವು
    0.36
    lines
    0.36
    toml
    0.36
    halb
    0.35
    vius
    0.35
    arbre
    0.35
    POSITIVE LOGITS
     flexibles
    0.57
     flexible
    0.54
     EDUCATION
    0.52
     Flexibility
    0.50
     flexibilidad
    0.48
     flexibility
    0.48
    Education
    0.48
    EDUCATION
    0.46
     Attention
    0.45
     교육
    0.45
    Act Density 0.000%

    No Known Activations