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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ौन
    -0.07
     พร
    -0.06
    (Context
    -0.06
     đây
    -0.06
     herpes
    -0.06
     uname
    -0.06
     tutors
    -0.06
     condi
    -0.06
    ()!=
    -0.06
    ...");↵
    -0.06
    POSITIVE LOGITS
    ‌ی
    0.07
     contrary
    0.07
    :ｉ
    0.06
    няют
    0.06
    elle
    0.06
    これ
    0.06
    ्फ
    0.06
     탈
    0.06
    RuleContext
    0.06
    firm
    0.06
    Act Density 0.000%

    No Known Activations