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

    Neuronpedia

    INDEX
    Explanations

    abundance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.00
    ב
    0.98
    м
    0.95
     It
    0.88
    с
    0.88
    おそらく
    0.86
    م
    0.86
    पिछले
    0.84
     aliments
    0.82
     arrhythmias
    0.81
    POSITIVE LOGITS
    '
    1.32
    (
    1.25
    (“
    1.11
    5
    1.09
    in
    1.06
    শালী
    1.02
    EL
    0.99
     watchlist
    0.98
    i
    0.98
    iella
    0.97
    Act Density 0.024%

    No Known Activations