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

    Neuronpedia

    INDEX
    Explanations

    ice

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “ice” when it appears in the context of “ice hockey.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     `/
    -0.07
    .NVarChar
    -0.06
     \/
    -0.06
    集团
    -0.06
    kud
    -0.06
     hav
    -0.06
     brisk
    -0.06
     endowed
    -0.06
    xec
    -0.06
     Vulcan
    -0.06
    POSITIVE LOGITS
    感じ
    0.07
    notated
    0.07
     Snow
    0.06
     disclosures
    0.06
    ewire
    0.06
     Podesta
    0.06
    κολ
    0.06
     attracting
    0.06
    mn
    0.06
     snow
    0.06
    Act Density 0.002%

    No Known Activations