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

    Neuronpedia

    INDEX
    Explanations

    explicit content or specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questions
    0.47
     질문
    0.44
     ethos
    0.43
     గుర్తు
    0.42
     вопросы
    0.42
     ухуд
    0.42
     HIV
    0.41
     Questions
    0.41
     perguntas
    0.41
     thumbs
    0.41
    POSITIVE LOGITS
    ید
    0.48
    كر
    0.48
     nawet
    0.47
    So
    0.47
    ور
    0.47
    And
    0.47
    Τα
    0.47
    Witam
    0.47
    arski
    0.46
     کرکے
    0.46
    Act Density 0.008%

    No Known Activations