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

    Neuronpedia

    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash

    The neuron fires on temperature- and heat-related words (e.g. “boiling,” “hot,” “degrees,” “warm,” “greased,” etc.) in cooking instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ail
    -0.07
    -0.07
    .spi
    -0.07
     incomes
    -0.06
    _empty
    -0.06
    JOIN
    -0.06
     registration
    -0.06
    -profit
    -0.06
    ails
    -0.06
    bi
    -0.06
    POSITIVE LOGITS
     Sears
    0.07
     أق
    0.06
     Dra
    0.06
    扩
    0.06
    稍
    0.06
     attire
    0.06
     fors
    0.06
    ايت
    0.06
     Dave
    0.06
     موب
    0.06
    Act Density 0.004%

    No Known Activations