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

    Neuronpedia

    INDEX
    Explanations

    route and redirect actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.45
    rianças
    0.43
     Champs
    0.42
     अंडे
    0.41
    Eggs
    0.40
     Eggs
    0.40
     டீ
    0.40
    barS
    0.39
     /ˈ
    0.39
    ś
    0.38
    POSITIVE LOGITS
    ابي
    0.44
    겟
    0.41
     homepage
    0.41
    ირი
    0.40
     Homepage
    0.39
     dow
    0.38
    GetName
    0.38
    _:
    0.37
    标识
    0.37
    魏
    0.37
    Act Density 0.001%

    No Known Activations