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

    Neuronpedia

    INDEX
    Explanations

    academic qualifications and fields of study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irrit
    0.74
     redness
    0.70
     takt
    0.68
     clotting
    0.68
     azalt
    0.66
     раздра
    0.65
     умень
    0.65
    防止
    0.64
     resposta
    0.64
     callous
    0.64
    POSITIVE LOGITS
     Graduate
    1.53
     graduate
    1.49
    Graduate
    1.48
     undergraduate
    1.42
     University
    1.36
     Undergraduate
    1.32
     Faculty
    1.30
     postgraduate
    1.29
     graduates
    1.28
     university
    1.28
    Act Density 0.186%

    No Known Activations