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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data, including ratios, magnifications, and other quantitative measures

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

    magnification and scale values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.41
     الأخ
    -0.40
    喜
    -0.39
     الاخ
    -0.38
     INC
    -0.38
    IC
    -0.37
    Avan
    -0.37
    مؤ
    -0.36
     Inc
    -0.36
     joaat
    -0.36
    POSITIVE LOGITS
    BeginContext
    0.57
     ब्रेकडाउन
    0.54
     ModelExpression
    0.52
    Хьажоргаш
    0.52
     الرياضيه
    0.51
    addPreferredGap
    0.51
     mijne
    0.49
    WriteLiteral
    0.48
    Билгалдахарш
    0.47
     שוליים
    0.47
    Act Density 0.040%

    No Known Activations