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

    Neuronpedia

    INDEX
    Explanations

    average value or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هذا
    0.52
     ഈ
    0.49
     эту
    0.47
     هذه
    0.46
     questa
    0.46
     ఈ
    0.45
     इस
    0.45
    এই
    0.43
     questo
    0.43
    這一
    0.43
    POSITIVE LOGITS
    看法
    0.43
     செயற்ப
    0.42
    ts
    0.41
    措置
    0.41
    am
    0.40
    efois
    0.40
    亳
    0.40
    ouli
    0.40
    နစ်
    0.39
    f
    0.39
    Act Density 0.015%

    No Known Activations