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

    Neuronpedia

    INDEX
    Explanations

    reality and objectivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    К
    -0.06
    ارک
    -0.06
     своїх
    -0.06
     vulgar
    -0.06
     Santos
    -0.06
    ショ
    -0.06
     Cler
    -0.06
     getters
    -0.06
     plagiarism
    -0.06
    Ｃ
    -0.06
    POSITIVE LOGITS
    .updateDynamic
    0.06
     ustanov
    0.06
     Breitbart
    0.06
    ตอน
    0.06
     лиш
    0.06
     پوش
    0.06
    '],$_
    0.06
     cigarette
    0.06
     esa
    0.06
     imageUrl
    0.06
    Act Density 0.033%

    No Known Activations