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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ceived
    -0.07
     остров
    -0.07
    自由
    -0.06
     Öz
    -0.06
     gọn
    -0.06
    แนะ
    -0.06
    linkedin
    -0.06
     دل
    -0.06
     seeks
    -0.06
    范围
    -0.06
    POSITIVE LOGITS
    @Data
    0.07
    Não
    0.06
     mental
    0.06
    ёт
    0.06
     nuit
    0.06
     shortcuts
    0.06
    __":↵
    0.06
    .waitKey
    0.06
    .asInstanceOf
    0.06
     Neuro
    0.06
    Act Density 0.114%

    No Known Activations