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

    Neuronpedia

    INDEX
    Explanations

    government performance protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    및
    0.43
     ACTIVITY
    0.41
     lø
    0.40
     جنگ
    0.39
     مطلب
    0.39
    لیم
    0.38
    ACTIVITY
    0.38
     активности
    0.38
    suivant
    0.37
     తె
    0.37
    POSITIVE LOGITS
     began
    0.45
     crept
    0.44
     testified
    0.40
     seemed
    0.40
     hesitated
    0.40
     ventured
    0.39
     doth
    0.39
     fled
    0.39
    racting
    0.39
     wondered
    0.39
    Act Density 0.000%

    No Known Activations