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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on the hyphen in the “UTF-8” encoding string in XML/HTML declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mortal
    -0.06
    /people
    -0.06
     ROUND
    -0.06
     〜
    -0.06
    adaş
    -0.06
    'na
    -0.06
     Rounds
    -0.06
    umnos
    -0.06
     gist
    -0.06
    ulis
    -0.06
    POSITIVE LOGITS
     freedom
    0.07
    oon
    0.07
     examines
    0.06
    _INCREF
    0.06
     somebody
    0.06
    /manual
    0.06
     increased
    0.06
    _marker
    0.06
     acceptable
    0.06
    <li
    0.06
    Act Density 0.000%

    No Known Activations