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

    Neuronpedia

    INDEX
    Explanations

    one followed by note, web, hundred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    جع
    0.43
    Selling
    0.42
    rotl
    0.42
    Stan
    0.40
    نوع
    0.39
    able
    0.38
     qilish
    0.38
    Antoine
    0.37
     პრო
    0.37
    汼
    0.37
    POSITIVE LOGITS
     Hundred
    0.60
     One
    0.58
    ToOne
    0.58
     Of
    0.43
     Two
    0.42
     hundred
    0.39
     Percent
    0.39
     upped
    0.38
     Three
    0.38
     Million
    0.38
    Act Density 0.005%

    No Known Activations