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

    Neuronpedia

    INDEX
    Explanations

    places and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diff
    0.34
     Quantification
    0.34
    thirsty
    0.33
     লজ্জা
    0.32
    alysis
    0.32
     terribly
    0.32
     Highness
    0.32
     Not
    0.32
     Thorough
    0.32
     Well
    0.31
    POSITIVE LOGITS
     giardino
    0.34
    空调
    0.33
    駐車場
    0.33
    țiile
    0.32
    IntVar
    0.32
    PropertySheets
    0.32
    Iranian
    0.32
    तार
    0.31
     bookcases
    0.31
     porch
    0.31
    Act Density 0.000%

    No Known Activations