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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ்டர்
    -0.08
     сделки
    -0.08
     sõ
    -0.08
     geçirilen
    -0.08
     यांच्या
    -0.08
     lessen
    -0.08
     ล้าน
    -0.08
     લઇ
    -0.07
    κών
    -0.07
    )?.
    -0.07
    POSITIVE LOGITS
     #↵↵
    0.10
     #↵
    0.09
     Inicial
    0.09
     Aquí
    0.09
     Settings
    0.08
     Aqui
    0.08
     Voici
    0.08
     Dub
    0.08
     --↵↵
    0.08
     Cela
    0.07
    Act Density 0.178%

    No Known Activations