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

    Neuronpedia

    INDEX
    Explanations

    elements relating to specific content or provisions in documents

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

    contains following provisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Демографія
    -0.59
     المعيارى
    -0.54
    HtmlAttribute
    -0.49
    shafen
    -0.48
     AssemblyTitle
    -0.48
    dimos
    -0.47
    Einf
    -0.46
     Audiodateien
    -0.46
    endphp
    -0.45
    lofen
    -0.45
    POSITIVE LOGITS
     contains
    0.81
     contain
    0.75
     Contains
    0.69
    contains
    0.66
     containing
    0.66
     contained
    0.65
    Contain
    0.65
     enthalten
    0.62
     Contain
    0.61
     bevat
    0.61
    Act Density 0.161%

    No Known Activations