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

    Neuronpedia

    INDEX
    Explanations

    colon cancer and polyps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.80
    در
    0.77
    K
    0.70
    ای
    0.66
    yı
    0.61
    D
    0.60
    쿠
    0.60
    "<
    0.59
    VE
    0.59
    DC
    0.59
    POSITIVE LOGITS
     colitis
    0.81
     colorectal
    0.67
     it
    0.63
    enary
    0.59
    spiration
    0.58
    eries
    0.56
    ifies
    0.55
     constipation
    0.55
     fecal
    0.55
    <0x80>
    0.54
    Act Density 0.002%

    No Known Activations