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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.78
     וכ
    0.76
    ra
    0.74
    ма
    0.73
    ین
    0.66
    с
    0.65
    з
    0.64
    ر
    0.62
    ก
    0.62
    sion
    0.61
    POSITIVE LOGITS
    zelfde
    0.90
    로운
    0.75
    ানি
    0.60
    ною
    0.59
     fø
    0.58
    ਾਬ
    0.58
    ći
    0.57
    롭게
    0.57
    ably
    0.57
    簟
    0.57
    Act Density 0.001%

    No Known Activations