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

    Neuronpedia

    INDEX
    Explanations

    weather forecast locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̵
    0.31
    県の
    0.29
     そんな
    0.29
     seroton
    0.28
     conexão
    0.27
    फरी
    0.26
     نتی
    0.26
    acariy
    0.26
     compréhension
    0.26
     İlçesi
    0.26
    POSITIVE LOGITS
    라
    0.31
     the
    0.30
     като
    0.30
     Agg
    0.30
     racism
    0.30
    ್ಯೂ
    0.30
     honest
    0.29
    0
    0.29
    mysql
    0.29
    프로
    0.29
    Act Density 0.003%

    No Known Activations