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

    Neuronpedia

    INDEX
    Explanations

    llvm:: functions, C++ code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Archer
    0.43
     Name
    0.41
     изменений
    0.40
    ческую
    0.40
     cyl
    0.39
     Сим
    0.39
     comet
    0.39
     dedo
    0.39
     Comet
    0.39
     let
    0.38
    POSITIVE LOGITS
    ateri
    0.47
    ahooks
    0.46
    agonal
    0.45
    ipennis
    0.45
    bromide
    0.44
    ')$
    0.42
    abbe
    0.42
    액
    0.42
    rosine
    0.41
     चाहि
    0.41
    Act Density 0.000%

    No Known Activations