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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    oai_token-act-pair · gemini-2.0-flash

    questions and answers

    np_max-act · gemini-2.0-flash

    answer

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     trơn
    -0.42
    ◄
    -0.41
     pris
    -0.40
    MLLoader
    -0.40
    نام
    -0.40
    度の
    -0.39
    Espèce
    -0.39
     pylori
    -0.39
     rather
    -0.38
     Barber
    -0.36
    POSITIVE LOGITS
     beginnetje
    0.88
    <bos>
    0.88
    FAQs
    0.85
    Datuak
    0.83
     nahilalakip
    0.81
     FAQ
    0.80
     FAQs
    0.80
     >=",
    0.79
     surla
    0.79
    FAQ
    0.77
    Act Density 0.937%

    No Known Activations