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

    Neuronpedia

    INDEX
    Explanations

    conditional logic and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    实
    0.40
    Charged
    0.38
    TR
    0.37
    え
    0.37
    まあ
    0.37
    ется
    0.37
    Lin
    0.37
    본
    0.37
    힐
    0.37
    内
    0.37
    POSITIVE LOGITS
    ୍କ
    0.57
     nitrification
    0.52
     brunes
    0.52
     cowboys
    0.52
    ments
    0.50
     मोहो
    0.50
    抂
    0.50
    狧
    0.49
     Kow
    0.48
    ępow
    0.48
    Act Density 0.000%

    No Known Activations