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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doe
    -0.07
     Fou
    -0.07
     setter
    -0.07
    /mL
    -0.07
     dol
    -0.06
     Mapping
    -0.06
    er
    -0.06
     Lunar
    -0.06
    ์ว
    -0.06
     Endpoint
    -0.06
    POSITIVE LOGITS
     statistics
    0.09
     Statistics
    0.08
    асс
    0.08
     stats
    0.08
    	stats
    0.07
    sk
    0.07
     그의
    0.07
    TS
    0.07
    agma
    0.07
     stones
    0.06
    Act Density 0.007%

    No Known Activations