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

    Neuronpedia

    INDEX
    Explanations

    each, every, listed, all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fehler
    0.35
     সংবাদ
    0.35
    する方法
    0.35
    ImgBoard
    0.34
    agh
    0.34
    الن
    0.34
     ПРО
    0.33
    君
    0.33
    的情
    0.33
    やら
    0.33
    POSITIVE LOGITS
     each
    0.49
    Each
    0.42
     listed
    0.41
    each
    0.41
    各
    0.40
     Each
    0.40
    แต่ละ
    0.39
     các
    0.38
     corresponding
    0.38
     mỗi
    0.37
    Act Density 0.485%

    No Known Activations