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

    Neuronpedia

    INDEX
    Explanations

    advisory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    并在
    -0.07
    (nome
    -0.06
    出席
    -0.06
     progressing
    -0.06
     П
    -0.06
     criança
    -0.06
    енн
    -0.06
    .dot
    -0.06
    aco
    -0.06
    .Panel
    -0.06
    POSITIVE LOGITS
     имеет
    0.08
    叨
    0.07
     policemen
    0.07
     files
    0.07
    得到有效
    0.07
     advisory
    0.07
    二手
    0.07
     ağır
    0.07
     Output
    0.07
     deletes
    0.07
    Act Density 0.002%

    No Known Activations