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

    Neuronpedia

    INDEX
    Explanations

    ordering lists, increase, decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fungsi
    0.43
    también
    0.41
     wunder
    0.40
    슐
    0.40
     importanti
    0.39
    oplasm
    0.39
     importantes
    0.39
    ╼
    0.39
     preoccup
    0.38
    thats
    0.38
    POSITIVE LOGITS
     decrease
    0.48
     increase
    0.47
    decrease
    0.43
     Decrease
    0.42
     Increase
    0.42
     overtime
    0.41
     사용하여
    0.39
    opposite
    0.39
    提高
    0.38
     Showing
    0.38
    Act Density 0.000%

    No Known Activations