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

    Neuronpedia

    INDEX
    Explanations

    across and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஒவ்வ
    0.47
     நல்லது
    0.47
     động
    0.42
     وړیا
    0.41
    各有
    0.41
     Each
    0.41
     полную
    0.40
    ('-
    0.40
     каждым
    0.40
    榃
    0.40
    POSITIVE LOGITS
     across
    0.63
     spectrum
    0.56
     different
    0.53
    整个
    0.53
    across
    0.50
    Across
    0.50
    整個
    0.47
     diferentes
    0.47
     всей
    0.46
     geographies
    0.46
    Act Density 0.010%

    No Known Activations