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

    Neuronpedia

    INDEX
    Explanations

    special effects and visuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uranium
    0.73
     moistur
    0.73
     chocolate
    0.71
     misdemeanor
    0.70
     nerdy
    0.70
     mahogany
    0.69
     dermatology
    0.68
     savory
    0.68
     parka
    0.68
     sushi
    0.68
    POSITIVE LOGITS
    Effects
    0.92
    w
    0.89
    p
    0.89
     efeitos
    0.88
     effects
    0.88
    effects
    0.87
     effets
    0.87
    on
    0.86
     effetti
    0.86
    c
    0.84
    Act Density 0.018%

    No Known Activations