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

    Neuronpedia

    INDEX
    Explanations

    brain, wide, plaid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ход
    0.56
    ീല
    0.50
    पत्र
    0.46
    ้าว
    0.46
    実際の
    0.46
     odc
    0.46
    ил
    0.46
    стры
    0.45
    етка
    0.45
    زیز
    0.45
    POSITIVE LOGITS
    empê
    0.48
    ng
    0.48
     affaires
    0.46
     ಕ
    0.46
     resentment
    0.45
    ndes
    0.45
    <a>
    0.44
    ment
    0.44
    ne
    0.44
    es
    0.44
    Act Density 0.001%

    No Known Activations