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

    Neuronpedia

    INDEX
    Explanations

    prostate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leur
    -0.07
     laugh
    -0.07
    	read
    -0.07
     welcome
    -0.07
     engineer
    -0.06
     отдел
    -0.06
    );}↵
    -0.06
     ders
    -0.06
    	done
    -0.06
    .access
    -0.06
    POSITIVE LOGITS
     prostate
    0.15
    zheimer
    0.07
     Estate
    0.07
     روان
    0.07
    xpath
    0.07
    -figure
    0.06
    state
    0.06
    STATE
    0.06
     prostitu
    0.06
    姓名
    0.06
    Act Density 0.002%

    No Known Activations