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

    Neuronpedia

    INDEX
    Explanations

    know anything or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spending
    0.38
     emojis
    0.37
     taxpayer
    0.36
     RJ
    0.36
     Spending
    0.35
     Gaga
    0.35
     victims
    0.35
     unsolicited
    0.35
     victimes
    0.34
     वॉइस
    0.34
    POSITIVE LOGITS
    Apr
    0.36
    Freeze
    0.33
    тун
    0.32
    freeze
    0.31
    anything
    0.31
    änt
    0.31
    bindo
    0.31
    izacja
    0.31
    ntgen
    0.31
    任何
    0.30
    Act Density 0.002%

    No Known Activations