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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surf
    -0.07
     yazı
    -0.07
    検
    -0.07
     سری
    -0.06
    _Err
    -0.06
     결정
    -0.06
     verse
    -0.06
     auch
    -0.06
    >Hello
    -0.06
    ［
    -0.06
    POSITIVE LOGITS
    liness
    0.06
    Tonight
    0.06
    Job
    0.06
    .dll
    0.06
    Invoice
    0.06
     disclaimer
    0.06
    jdbc
    0.06
    홍
    0.06
    rowse
    0.06
    рина
    0.06
    Act Density 0.143%

    No Known Activations