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

    Neuronpedia

    INDEX
    Explanations

    efficiently incorporates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.06
    democratic
    1.02
    i
    0.99
     onCreateView
    0.98
    antiation
    0.97
    ं
    0.94
    t
    0.93
    al
    0.89
    ы
    0.89
     NSUTF
    0.88
    POSITIVE LOGITS
     Airtel
    1.05
    窕
    1.05
     Cassini
    1.04
     Laurent
    1.04
     Bourbon
    1.03
    𝐡
    1.03
     Certification
    1.02
     Worcestershire
    1.01
     Berkshire
    1.01
    𝙧
    1.00
    Act Density 0.000%

    No Known Activations