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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases about naming or being called—e.g. “name,” “call,” “give (me) a name,” “you can call me,” and “prefer.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .use
    -0.07
     Seven
    -0.06
     Va
    -0.06
     va
    -0.06
    ابة
    -0.06
    139
    -0.06
    än
    -0.06
    _the
    -0.06
    /
    -0.06
    _plus
    -0.06
    POSITIVE LOGITS
    Datos
    0.08
    .SUCCESS
    0.07
     pBuffer
    0.07
     webhook
    0.07
     піс
    0.06
    .Butter
    0.06
     sortable
    0.06
     Pick
    0.06
     adorned
    0.06
    _imp
    0.06
    Act Density 0.010%

    No Known Activations