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

    Neuronpedia

    INDEX
    Explanations

    start of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ג
    0.57
    ר
    0.53
    uern
    0.52
    ת
    0.52
    ਰੇ
    0.52
    د
    0.52
    都没有
    0.52
    ุ
    0.50
    т
    0.50
    ாக
    0.49
    POSITIVE LOGITS
    কে
    0.56
    oke
    0.50
     fundraisers
    0.49
     Examination
    0.48
     تھا
    0.48
     څه
    0.47
    getRedTeam
    0.47
     Scheduled
    0.47
     \
    0.46
     Safegu
    0.46
    Act Density 0.000%

    No Known Activations