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

    Neuronpedia

    INDEX
    Explanations

    it is essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^{+}(
    0.42
    rctx
    0.41
    ToListAsync
    0.41
    lastval
    0.40
    LOTREntity
    0.40
     txtbtn
    0.39
    ەند
    0.39
    파일명
    0.39
     //</
    0.38
    "+"|".
    0.38
    POSITIVE LOGITS
     Complement
    0.60
     complements
    0.57
     complement
    0.56
     complementary
    0.52
     supplements
    0.49
    complement
    0.49
    Complement
    0.48
     complementar
    0.47
     Cannot
    0.46
     complementing
    0.45
    Act Density 0.001%

    No Known Activations