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

    Neuronpedia

    INDEX
    Explanations

    new levels and opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eventually
    0.75
    Eventually
    0.73
     mx
    0.68
     Minimize
    0.68
     lapply
    0.67
    概
    0.67
    ()/
    0.66
     eventual
    0.66
     minimizar
    0.65
    儸
    0.64
    POSITIVE LOGITS
    新たな
    2.58
     new
    2.49
     새로운
    2.39
    全新的
    2.34
     nuevas
    2.31
    新的
    2.30
    new
    2.23
     nuovi
    2.21
     nuove
    2.21
     nieuwe
    2.15
    Act Density 0.124%

    No Known Activations