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

    Neuronpedia

    INDEX
    Explanations

    based on datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.47
    (
    0.46
    /
    0.46
     Alibaba
    0.45
     Ad
    0.42
     Spotify
    0.42
    ology
    0.41
     Amazon
    0.41
     sheer
    0.41
     Custom
    0.40
    POSITIVE LOGITS
    Ainsi
    0.49
    پردا
    0.49
    ার্ভ
    0.47
    Limite
    0.46
    きっと
    0.46
    拁
    0.45
     당신
    0.45
    نيك
    0.45
    фика
    0.45
    ｖ
    0.45
    Act Density 0.045%

    No Known Activations