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

    Neuronpedia

    INDEX
    Explanations

    best estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instantly
    0.46
    Instant
    0.45
    دە
    0.44
     instant
    0.43
    instant
    0.43
     instantaneously
    0.40
     एकदम
    0.39
    最新的
    0.39
     instantaneous
    0.39
    Stu
    0.39
    POSITIVE LOGITS
     we
    0.50
    我们
    0.46
     мы
    0.46
     chúng
    0.46
     nossa
    0.45
     우리
    0.42
     ჩვენ
    0.41
     Henn
    0.41
     हम
    0.41
    yoruz
    0.41
    Act Density 0.000%

    No Known Activations