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

    Neuronpedia

    INDEX
    Explanations

    initial phases or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niez
    1.60
     자
    1.18
     teljes
    1.17
    이제
    1.17
     wiele
    1.17
     helper
    1.14
     surfactants
    1.14
     된
    1.13
    х
    1.13
     pr
    1.13
    POSITIVE LOGITS
    ting
    1.15
    روی
    1.11
    рыва
    1.09
    LayoutPanel
    1.04
    пу
    1.04
    mittag
    1.04
    egg
    1.02
    time
    1.00
    bicyclo
    0.99
    r
    0.98
    Act Density 0.001%

    No Known Activations