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
    vents
    -0.07
    _gshared
    -0.07
    _WARN
    -0.07
    gnu
    -0.06
     bigot
    -0.06
    uge
    -0.06
    -vis
    -0.06
    伝
    -0.06
     sư
    -0.06
    าตรฐาน
    -0.06
    POSITIVE LOGITS
     культуры
    0.06
     некоторые
    0.06
     �
    0.06
     amended
    0.06
     monitor
    0.06
     jackets
    0.06
    戴
    0.06
    .directory
    0.06
    kl
    0.06
     Lowell
    0.06
    Act Density 0.000%

    No Known Activations