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

    Neuronpedia

    INDEX
    Explanations

    formed through a reality show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carelessly
    0.44
     safest
    0.44
     Lankan
    0.43
     blanket
    0.40
     sleepers
    0.40
     needlessly
    0.39
     Evet
    0.38
     damning
    0.38
     limitless
    0.38
     discarded
    0.37
    POSITIVE LOGITS
    谚
    0.45
    Histogram
    0.43
    سبب
    0.42
    affeine
    0.42
    munition
    0.42
    britannien
    0.41
     governo
    0.40
     উপস
    0.40
     gouvernement
    0.40
     percobaan
    0.40
    Act Density 0.006%

    No Known Activations