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

    Neuronpedia

    INDEX
    Explanations

    test cases and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tested
    0.57
     اختبار
    0.52
     getest
    0.52
     tests
    0.47
     тести
    0.47
     Tested
    0.46
     testen
    0.45
     পরীক্ষা
    0.44
    เหลือ
    0.43
     آزمایش
    0.41
    POSITIVE LOGITS
    NG
    0.54
     cases
    0.54
    cases
    0.54
    case
    0.52
    Cases
    0.48
     Cases
    0.47
     casos
    0.45
     case
    0.44
    Caso
    0.44
    ケース
    0.43
    Act Density 0.005%

    No Known Activations