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

    Neuronpedia

    INDEX
    Explanations

    list format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewSet
    0.97
     Verhältnis
    0.95
     loving
    0.94
     връ
    0.93
    期
    0.93
     scaled
    0.92
     лоша
    0.92
     estuvo
    0.90
    アート
    0.90
    हिम
    0.90
    POSITIVE LOGITS
    ENER
    1.56
    ENING
    1.56
    icle
    1.49
    unstyled
    1.48
    PreferredItem
    1.38
    icles
    1.35
     бумаги
    1.27
    ened
    1.25
    PopupWindowStyle
    1.25
    henes
    1.23
    Act Density 0.127%

    No Known Activations