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

    Neuronpedia

    INDEX
    Explanations

    concept of all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Every
    1.06
    Every
    1.02
    Everyone
    1.00
     Everyone
    0.97
    Everybody
    0.96
     Everybody
    0.90
    EVERY
    0.89
    every
    0.85
     everybody
    0.83
    IVED
    0.82
    POSITIVE LOGITS
     all
    3.54
    all
    2.98
     All
    2.56
    All
    2.55
    ALL
    2.25
     ALL
    2.24
     allemaal
    2.18
     모두
    1.80
     всех
    1.74
     все
    1.70
    Act Density 0.020%

    No Known Activations