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

    Neuronpedia

    INDEX
    Explanations

    scope and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shopify
    0.46
     Immutable
    0.43
     ویئر
    0.41
     IDs
    0.40
     Frobenius
    0.40
     বঙ্গবন্ধ
    0.39
    BUGFS
    0.38
     století
    0.38
    числения
    0.38
     Sts
    0.37
    POSITIVE LOGITS
    รรม
    0.40
     menurun
    0.38
     EDUCATION
    0.37
    }{
    0.36
    Portfolio
    0.36
    സും
    0.36
    ատ
    0.36
    Investment
    0.36
    教育
    0.36
     supplemental
    0.36
    Act Density 0.001%

    No Known Activations