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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and patterns of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    frequency, time, and occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.52
    ۠
    -0.52
    tonode
    -0.49
    FailureListener
    -0.48
    ckså
    -0.48
    ➯
    -0.48
    veria
    -0.47
     selamat
    -0.45
    出来
    -0.45
    fromnode
    -0.45
    POSITIVE LOGITS
    WireFormatLite
    0.51
    Whenever
    0.38
     mornings
    0.37
    TextBoxColumn
    0.36
     Whenever
    0.35
     hang
    0.34
     daily
    0.33
     frequent
    0.33
    +#+#
    0.32
    UpInside
    0.32
    Act Density 0.087%

    No Known Activations