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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afflicted
    -0.07
    andr
    -0.07
    "(
    -0.06
    ,—
    -0.06
    Tk
    -0.06
    itt
    -0.06
     road
    -0.06
    "C
    -0.06
     Mp
    -0.06
     documented
    -0.06
    POSITIVE LOGITS
    ็นต
    0.07
     Squad
    0.06
    (Utils
    0.06
    lili
    0.06
    _Thread
    0.06
    كن
    0.06
    كم
    0.06
    ([\
    0.06
    ूच
    0.06
    圭圭
    0.06
    Act Density 0.001%

    No Known Activations