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

    Neuronpedia

    INDEX
    Explanations

    aforementioned or above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সঙ্গে
    0.37
     hervorrag
    0.37
    CANADA
    0.36
    Canada
    0.36
    当該
    0.36
    Gün
    0.35
     respectivos
    0.35
    यहां
    0.35
    פ
    0.35
    revalidator
    0.34
    POSITIVE LOGITS
     위의
    0.59
    上述
    0.57
     aforementioned
    0.54
    前面的
    0.53
     выше
    0.52
     above
    0.52
     위에
    0.51
    以上的
    0.49
    上面的
    0.48
    前面
    0.46
    Act Density 0.136%

    No Known Activations