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

    Neuronpedia

    INDEX
    Explanations

    relative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SafeArea
    0.42
     stagn
    0.39
     뭔
    0.37
     Hence
    0.37
     bisa
    0.37
     Gos
    0.37
     Doming
    0.36
     ré
    0.36
     harnessing
    0.36
     Merci
    0.35
    POSITIVE LOGITS
     Technical
    0.39
     technical
    0.39
    ist
    0.38
    iquant
    0.37
    KeepOriginal
    0.37
    ished
    0.37
    scribers
    0.36
    igus
    0.36
    quisa
    0.36
    相対
    0.36
    Act Density 0.001%

    No Known Activations