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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “short.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Marg
    -0.07
    more
    -0.07
    поч
    -0.07
    (Char
    -0.06
     incarcerated
    -0.06
    idlo
    -0.06
     plá
    -0.06
     deline
    -0.06
     dads
    -0.06
     shedding
    -0.06
    POSITIVE LOGITS
     contempt
    0.06
     Astronomy
    0.06
    	function
    0.06
    //'
    0.06
     Browser
    0.06
    	sp
    0.06
    EMP
    0.06
    DIG
    0.06
    _CC
    0.06
    CRE
    0.06
    Act Density 0.013%

    No Known Activations