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

    Neuronpedia

    INDEX
    Explanations

    exploring new ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ultimatum
    0.70
     修改
    0.68
    焊
    0.67
    ؤال
    0.66
    สัญญาณ
    0.66
    改成
    0.66
     Concise
    0.66
    licting
    0.65
    修改
    0.65
    erequisite
    0.64
    POSITIVE LOGITS
     explore
    2.72
     exploring
    2.64
     exploration
    2.53
    Explore
    2.49
     Explore
    2.43
    explore
    2.38
     immerse
    2.27
    Exploring
    2.27
     explor
    2.26
     Exploring
    2.26
    Act Density 1.067%

    No Known Activations