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

    Neuronpedia

    INDEX
    Explanations

    tabular data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نان
    0.46
    </h2>
    0.44
    enean
    0.42
     الأخيرة
    0.42
    เนิน
    0.42
     وسائل
    0.41
    ED
    0.41
    [-
    0.41
    Role
    0.40
    ursday
    0.39
    POSITIVE LOGITS
    ین
    0.59
    ون
    0.53
    ید
    0.52
    ت
    0.52
    िश्वत
    0.49
    dincer
    0.46
    ี
    0.46
     토
    0.45
    𝒅
    0.45
     deflate
    0.44
    Act Density 0.007%

    No Known Activations