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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “colon” (as in colon, colonoscopy, colorectal, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unh
    -0.07
     Brent
    -0.07
    mrt
    -0.07
    ROLE
    -0.07
    ffa
    -0.07
     Іван
    -0.07
    ITTLE
    -0.07
    闪
    -0.07
     میک
    -0.06
     Jade
    -0.06
    POSITIVE LOGITS
     colon
    0.14
     Colon
    0.09
     Clinton
    0.08
    τον
    0.08
    alon
    0.08
    Clinton
    0.07
     colonization
    0.07
    Colon
    0.07
    ON
    0.07
    ör
    0.07
    Act Density 0.004%

    No Known Activations