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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron fires on the numeric time‐duration tokens (e.g. the minute:second track lengths) in album track listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    奶
    -0.06
     fanc
    -0.06
     fron
    -0.06
    των
    -0.06
     Grocery
    -0.06
    Details
    -0.06
     dull
    -0.06
    .Child
    -0.06
    _max
    -0.06
    阿
    -0.06
    POSITIVE LOGITS
    _decimal
    0.08
    MT
    0.07
    (&
    0.07
    ');↵↵↵
    0.06
    	record
    0.06
    "));
    0.06
    _prediction
    0.06
    >()->
    0.06
    #$
    0.06
    (Activity
    0.06
    Act Density 0.030%

    No Known Activations