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

    Neuronpedia

    INDEX
    Explanations

    festivals, regions, and specific cultures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dre
    0.62
    า
    0.62
    ो
    0.60
     филосо
    0.59
     ал
    0.59
    тр
    0.57
    drama
    0.57
    ia
    0.56
     т
    0.56
    owners
    0.56
    POSITIVE LOGITS
    的
    0.51
     TikTok
    0.50
    лях
    0.47
    éns
    0.47
    _
    0.47
    Bytes
    0.46
    ética
    0.46
     Byte
    0.45
     sortie
    0.45
     interval
    0.45
    Act Density 0.000%

    No Known Activations