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

    Neuronpedia

    INDEX
    Explanations

    document separators or markers indicating the start of relevant content

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

    Code snippets with symbols and numbers

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوابة
    -0.56
    AutoField
    -0.49
     مُعرِّف
    -0.49
    PreferredItem
    -0.48
     архивлан
    -0.47
    cur
    -0.46
    etak
    -0.46
    лык
    -0.45
     ModelExpression
    -0.43
    ArrowToggle
    -0.43
    POSITIVE LOGITS
    '}>
    0.80
    ')")
    0.71
     createSlice
    0.69
    }');
    0.69
    expandindo
    0.68
     المعيارى
    0.68
    '},
    0.66
    日閲覧
    0.65
    ')));
    0.64
    endphp
    0.63
    Act Density 0.171%

    No Known Activations