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

    Neuronpedia

    INDEX
    Explanations

    product descriptions for candles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proprie
    0.48
    elte
    0.48
    ORE
    0.47
    ри
    0.46
    Behavior
    0.46
    0.46
    Colleg
    0.46
     caractères
    0.45
     derel
    0.45
     hayvan
    0.44
    POSITIVE LOGITS
    ↵↵
    0.53
     And
    0.51
     wow
    0.48
     Rentals
    0.48
    jpg
    0.46
     클릭
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    !?
    0.46
     Clubs
    0.46
     Come
    0.45
    Act Density 0.003%

    No Known Activations