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

    Neuronpedia

    INDEX
    Explanations

    Hope you well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explanation
    0.55
     description
    0.49
     explicación
    0.48
     explanations
    0.47
     informatie
    0.46
     descrição
    0.46
     diagnoses
    0.46
     информация
    0.45
     توضی
    0.44
     penjelasan
    0.44
    POSITIVE LOGITS
    Enjoy
    0.54
     Enjoy
    0.48
     enjoy
    0.43
     enjoying
    0.42
    upp
    0.41
    enjoy
    0.41
     comienzan
    0.40
     즐
    0.39
    Introducing
    0.39
     youre
    0.38
    Act Density 0.001%

    No Known Activations