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

    Neuronpedia

    INDEX
    Explanations

    Internet/code-like text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voltage
    -0.08
     dependencies
    -0.07
     несколько
    -0.07
    <HTML
    -0.07
     educating
    -0.07
     burdens
    -0.07
     Ott
    -0.07
    RequestMapping
    -0.06
    */)↵
    -0.06
    ิโล
    -0.06
    POSITIVE LOGITS
    zent
    0.06
     çerçev
    0.06
    218
    0.06
    IN
    0.06
    ếu
    0.06
    loc
    0.06
    ו
    0.06
    GRID
    0.06
     lugar
    0.05
    ibi
    0.05
    Act Density 0.027%

    No Known Activations