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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оста
    0.40
    马
    0.39
    发生
    0.39
     संचालित
    0.37
     باقی
    0.37
     उपयोग
    0.37
    围绕
    0.37
     अधिकांश
    0.37
     Стар
    0.36
     majeure
    0.36
    POSITIVE LOGITS
    Explanation
    0.52
     explanation
    0.48
    answer
    0.47
     explan
    0.46
    Answer
    0.46
     answer
    0.45
     explicación
    0.44
     Explanation
    0.44
    explanation
    0.43
     answering
    0.42
    Act Density 0.000%

    No Known Activations