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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    the digit “2” in tokens (i.e. numeric occurrences of “2”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    666
    -0.07
     менее
    -0.07
    C
    -0.06
    intr
    -0.06
    殖
    -0.06
    FFFFFF
    -0.06
    这
    -0.06
     folding
    -0.06
    /examples
    -0.06
    urv
    -0.06
    POSITIVE LOGITS
     ether
    0.07
    chedules
    0.07
     srand
    0.07
    (null
    0.07
     Walls
    0.06
     account
    0.06
    .say
    0.06
    	items
    0.06
    闘
    0.06
     Pont
    0.06
    Act Density 0.001%

    No Known Activations