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

    Neuronpedia

    INDEX
    Explanations

    code data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Controls
    -0.08
     tavs
    -0.07
    _exc
    -0.06
    Second
    -0.06
     MOST
    -0.06
     muž
    -0.06
    otron
    -0.06
     بول
    -0.06
    Solver
    -0.06
    جمة
    -0.06
    POSITIVE LOGITS
    ların
    0.06
    \controllers
    0.06
    整个
    0.06
    StorageSync
    0.06
     near
    0.06
    metatable
    0.06
     employing
    0.06
     singapore
    0.06
     onların
    0.06
     Railroad
    0.06
    Act Density 0.003%

    No Known Activations