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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments with stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    소개
    -0.07
     choice
    -0.06
     Pros
    -0.06
    україн
    -0.06
    _asm
    -0.06
    ashi
    -0.06
     Tara
    -0.06
     UIT
    -0.06
    筋
    -0.06
     역사
    -0.05
    POSITIVE LOGITS
    (show
    0.07
     تعداد
    0.07
    _chars
    0.07
    %",↵
    0.06
    pectives
    0.06
     minOccurs
    0.06
     chlorine
    0.06
     Flyers
    0.06
    水平
    0.06
    WithType
    0.06
    Act Density 0.000%

    No Known Activations