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

    Neuronpedia

    INDEX
    Explanations

    new uses/products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Broken
    -0.07
     christmas
    -0.07
    ()).
    -0.07
     iron
    -0.07
    antha
    -0.07
    Spanish
    -0.06
    '))↵↵
    -0.06
     Concord
    -0.06
     oldukça
    -0.06
    .RES
    -0.06
    POSITIVE LOGITS
     dazu
    0.07
     табли
    0.06
    MN
    0.06
    mot
    0.06
    ед
    0.06
    EMENT
    0.06
    бот
    0.06
    译
    0.06
     jub
    0.06
     jewel
    0.06
    Act Density 0.131%

    No Known Activations