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

    Neuronpedia

    INDEX
    Explanations

    code keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."',
    0.30
    یں۔
    0.29
    ../../
    0.27
    ments
    0.27
    ."],
    0.27
    '.
    0.27
    ']])
    0.26
     onFailure
    0.26
    。“
    0.25
    ','"+
    0.25
    POSITIVE LOGITS
     noastră
    0.27
     période
    0.26
     reasons
    0.26
    鍑
    0.26
    ння
    0.26
    Ine
    0.25
    斫
    0.25
     périodes
    0.25
     granularity
    0.24
    频率
    0.24
    Act Density 0.431%

    No Known Activations