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

    Neuronpedia

    INDEX
    Explanations

    Mentions Obama

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on tokens related to food and drink—especially beer, brewing, and culinary terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     conservative
    -0.07
     observ
    -0.07
     Af
    -0.07
     lamp
    -0.07
     lawsuit
    -0.06
     Mir
    -0.06
     bundle
    -0.06
     phone
    -0.06
     MAC
    -0.06
     Lamp
    -0.06
    POSITIVE LOGITS
    Tôi
    0.07
    VES
    0.07
    LOY
    0.06
    modx
    0.06
     overwhelm
    0.06
    PLOY
    0.06
     cq
    0.06
     letz
    0.06
    CONF
    0.06
    esor
    0.06
    Act Density 0.063%

    No Known Activations