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

    Neuronpedia

    INDEX
    Explanations

    1 in X ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.70
    OOOO
    0.60
    IS
    0.59
    ﻌ
    0.59
    τα
    0.57
     go
    0.57
    Denmark
    0.57
     मैक्स
    0.56
    इस
    0.55
     commission
    0.55
    POSITIVE LOGITS
    вли
    0.71
    atkar
    0.67
    fehlung
    0.67
     antice
    0.66
    arif
    0.65
    洴
    0.64
    oron
    0.63
    افي
    0.62
     وكان
    0.62
     تھا
    0.60
    Act Density 0.001%

    No Known Activations