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

    Neuronpedia

    INDEX
    Explanations

    comma, and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kadınlar
    -0.07
    (value
    -0.07
    ，用
    -0.06
    害
    -0.06
     lời
    -0.06
    歯
    -0.06
     second
    -0.06
    呼ば
    -0.06
    黨
    -0.06
     học
    -0.06
    POSITIVE LOGITS
    .so
    0.06
    LOUD
    0.06
    .pref
    0.06
     mig
    0.06
    :",↵
    0.06
    <uint
    0.06
    सभ
    0.06
     ki
    0.06
    =max
    0.06
    ension
    0.05
    Act Density 0.015%

    No Known Activations