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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xcd
    -0.07
     blackout
    -0.07
     Request
    -0.06
     holidays
    -0.06
     chuyến
    -0.06
    Prim
    -0.06
    .prevent
    -0.06
    pag
    -0.06
     phái
    -0.06
    ivating
    -0.06
    POSITIVE LOGITS
    --[
    0.07
    conexao
    0.07
     الوطني
    0.06
    当然
    0.06
    Definitions
    0.06
    em
    0.06
    ++;
    0.06
    Sem
    0.06
    有什么
    0.06
    ічного
    0.06
    Act Density 0.079%

    No Known Activations