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

    Neuronpedia

    INDEX
    Explanations

    hugely significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convinc
    0.47
     જરૂ
    0.46
     ошибок
    0.46
     algebraica
    0.46
    襁
    0.45
    꼭
    0.44
     Scha
    0.44
     فرق
    0.44
     Fehler
    0.44
    Bishop
    0.44
    POSITIVE LOGITS
    )
    0.51
    ),
    0.51
    ជ្ជ
    0.49
    子
    0.47
    易
    0.47
    اس
    0.47
    ᒃ
    0.47
    د
    0.46
    하다
    0.46
    ி
    0.45
    Act Density 0.001%

    No Known Activations