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

    Neuronpedia

    INDEX
    Explanations

    endearment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grandparents
    -0.07
    qa
    -0.06
    чки
    -0.06
     Τζ
    -0.06
    .startDate
    -0.06
     елем
    -0.06
     Static
    -0.06
    ạch
    -0.06
    !!");↵
    -0.06
    /String
    -0.06
    POSITIVE LOGITS
    /js
    0.07
     생각
    0.07
     disjoint
    0.07
    عد
    0.06
    Sadly
    0.06
     사용
    0.06
    VN
    0.06
     recuper
    0.06
    �
    0.06
    ||||
    0.06
    Act Density 0.034%

    No Known Activations