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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soldier
    -0.07
    -pointer
    -0.07
    會
    -0.06
     devil
    -0.06
     cher
    -0.06
    converted
    -0.06
     Nah
    -0.06
    (circle
    -0.06
    _Bar
    -0.06
    eteria
    -0.06
    POSITIVE LOGITS
    )</
    0.06
     wiki
    0.06
     disqualified
    0.06
    廣
    0.06
    	rv
    0.06
     уяв
    0.06
    ＝
    0.06
     Å
    0.06
     mk
    0.06
    \AppData
    0.06
    Act Density 0.019%

    No Known Activations