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

    Neuronpedia

    INDEX
    Explanations

    wear away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ン
    0.81
     выполнение
    0.80
     combinação
    0.79
    кает
    0.78
     какое
    0.77
     обеспечение
    0.77
    щение
    0.75
     nomm
    0.75
    писок
    0.75
     ১৯৬৫
    0.74
    POSITIVE LOGITS
    ا
    0.79
    Fact
    0.78
    speople
    0.75
    Repl
    0.72
    letters
    0.70
    y
    0.70
    ୁ
    0.70
    RE
    0.69
    constraints
    0.69
    เสริม
    0.69
    Act Density 0.001%

    No Known Activations