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

    Neuronpedia

    INDEX
    Explanations

    FAQs and downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लिमिट
    0.71
    ர்வு
    0.70
    🤞
    0.69
    🙈
    0.68
     conflicting
    0.68
    ugno
    0.67
    箋
    0.66
    etermined
    0.65
    😩
    0.65
    ensibly
    0.64
    POSITIVE LOGITS
     News
    1.75
     news
    1.72
     FAQ
    1.66
     FAQs
    1.65
    News
    1.65
     NEWS
    1.60
     Contacts
    1.60
    Contacts
    1.57
     nieuws
    1.57
    Publications
    1.56
    Act Density 0.950%

    No Known Activations