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

    Neuronpedia

    INDEX
    Explanations

    text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CellStyle
    -0.07
    .isOn
    -0.06
     courageous
    -0.06
    .ONE
    -0.06
    [Y
    -0.06
     Neighbor
    -0.06
    [op
    -0.06
    Trash
    -0.06
     ホ
    -0.06
     dzi
    -0.06
    POSITIVE LOGITS
    软件
    0.07
     choisir
    0.07
    ileceğini
    0.06
     文章
    0.06
    ß
    0.06
    Compet
    0.06
     Jub
    0.06
     alla
    0.06
    significant
    0.06
    ورد
    0.06
    Act Density 0.170%

    No Known Activations