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

    Neuronpedia

    INDEX
    Explanations

    code and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рд
    0.51
     trifling
    0.50
    olverine
    0.48
     බල
    0.45
    туга
    0.45
    ത്യ
    0.45
     පිළිබ
    0.45
    ций
    0.44
    خة
    0.44
    يسي
    0.44
    POSITIVE LOGITS
     Esc
    0.52
    er
    0.50
    es
    0.50
     Twitter
    0.50
     Ins
    0.49
     city
    0.49
    Id
    0.49
     school
    0.49
     Immediate
    0.48
     Ha
    0.48
    Act Density 0.000%

    No Known Activations