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

    Neuronpedia

    INDEX
    Explanations

    you, your, offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ignor
    0.47
     deprive
    0.42
    isNull
    0.42
    мони
    0.41
    direita
    0.41
     ње
    0.41
    られました
    0.41
     ignor
    0.40
    னித
    0.40
    他們的
    0.40
    POSITIVE LOGITS
     You
    0.56
     you
    0.54
     Netflix
    0.49
     Firebase
    0.47
     Ingredient
    0.46
     আপনি
    0.45
     Take
    0.45
     Enjoy
    0.44
     Book
    0.43
     Song
    0.43
    Act Density 0.003%

    No Known Activations