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

    Neuronpedia

    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect words and phrases describing weather conditions (e.g., climate descriptors and temperature ranges).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    igmoid
    -0.07
     skeptical
    -0.07
    ín
    -0.07
     zeros
    -0.06
     sự
    -0.06
    δό
    -0.06
     filetype
    -0.06
    bi
    -0.06
    .Mongo
    -0.06
     myths
    -0.06
    POSITIVE LOGITS
    '],'
    0.06
    ".$
    0.06
    <P
    0.06
    frac
    0.06
    ?[
    0.06
     север
    0.06
    ()?.
    0.06
    URL
    0.06
    ा:
    0.06
     español
    0.06
    Act Density 0.017%

    No Known Activations