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

    Neuronpedia

    INDEX
    Explanations

    positive feelings and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perverse
    0.46
     הרו
    0.46
     yarı
    0.45
     парла
    0.45
     dictatorship
    0.44
     sayı
    0.44
    葢
    0.44
     uomini
    0.43
    ıp
    0.43
    ilerinin
    0.43
    POSITIVE LOGITS
     shipments
    0.45
     valuable
    0.44
     available
    0.41
    <\
    0.40
     everyday
    0.39
    符合
    0.39
     Scripps
    0.38
     applied
    0.38
     plant
    0.38
     Amtrak
    0.38
    Act Density 0.005%

    No Known Activations