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

    Neuronpedia

    INDEX
    Explanations

    Okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     მაგ
    0.41
     ஆன்
    0.39
    Bets
    0.39
     Juli
    0.38
     foot
    0.36
     personalization
    0.36
    敎
    0.36
    !.
    0.36
    :\
    0.35
    :'
    0.35
    POSITIVE LOGITS
     Okay
    0.53
    Okay
    0.50
    okay
    0.49
     okay
    0.49
    分享
    0.43
    StatusOK
    0.43
     ok
    0.42
    OK
    0.42
     OK
    0.41
    ដែ
    0.40
    Act Density 0.000%

    No Known Activations