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

    Neuronpedia

    INDEX
    Explanations

    levels and stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ger
    0.40
    skih
    0.38
    τικής
    0.38
    Trashed
    0.38
    df
    0.38
    top
    0.38
    numbered
    0.38
    door
    0.34
    με
    0.34
     tertiary
    0.34
    POSITIVE LOGITS
     này
    0.45
    :
    0.41
     précédente
    0.39
    MetaObject
    0.38
    นี้
    0.38
     ito
    0.38
     dowol
    0.37
     cette
    0.37
    ：《
    0.37
     一个
    0.37
    Act Density 0.014%

    No Known Activations