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

    Neuronpedia

    INDEX
    Explanations

    no simple answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sleeps
    0.68
    പ്പ
    0.66
     Sour
    0.65
    statusbar
    0.63
     freshness
    0.63
    ʋ
    0.62
     fewer
    0.60
    ौनक
    0.60
     sour
    0.60
     treats
    0.60
    POSITIVE LOGITS
    Broad
    0.70
     broad
    0.69
    no
    0.68
     وسی
    0.66
     BROAD
    0.63
     simply
    0.62
    broad
    0.62
     whatever
    0.61
     Wahrheit
    0.59
    General
    0.59
    Act Density 0.041%

    No Known Activations