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

    Neuronpedia

    INDEX
    Explanations

    nga

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -1.14
    nga
    -0.79
     par
    -0.69
    a
    -0.67
    nya
    -0.62
    ся
    -0.55
     para
    -0.53
    es
    -0.52
    ↵
    -0.52
    t
    -0.50
    POSITIVE LOGITS
     myſelf
    1.09
    CloseOperation
    1.05
     Efq
    1.05
     Jefus
    1.03
     iſt
    0.99
     purpoſe
    0.98
     ſche
    0.97
     whoſe
    0.94
     itſelf
    0.94
     fevere
    0.93
    Act Density 1.281%

    No Known Activations