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

    Neuronpedia

    INDEX
    Explanations

    aportado / aportan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    1.30
    iv
    1.20
    h
    1.16
    ă
    1.13
    اه
    1.10
     어린이
    1.04
    ıya
    1.02
     آ
    1.00
     an
    0.95
     था
    0.93
    POSITIVE LOGITS
    لية
    1.28
    ្សែ
    1.25
    stwo
    1.25
    ről
    1.21
    лева
    1.12
     linkCell
    1.07
    ో
    1.05
    ства
    1.04
    ン
    1.04
    亼
    1.04
    Act Density 0.000%

    No Known Activations