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

    Neuronpedia

    INDEX
    Explanations

    academic and scholastic research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ми
    0.61
    گ
    0.59
    وم
    0.58
    Три
    0.58
    三十
    0.54
    Га
    0.54
    ைட்
    0.53
     éton
    0.53
     tät
    0.52
    oną
    0.52
    POSITIVE LOGITS
     scholastic
    0.67
     university
    0.64
     academic
    0.63
    academic
    0.62
    university
    0.61
    🎓
    0.61
     college
    0.60
    )
    0.59
     scholarly
    0.58
     academically
    0.57
    Act Density 0.094%

    No Known Activations