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

    Neuronpedia

    INDEX
    Explanations

    research citations

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “nutrients,” i.e. when the text refers to nutrient-related terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    match
    -0.06
     identifying
    -0.06
    )NSString
    -0.06
    elve
    -0.06
    reat
    -0.06
    되
    -0.06
    =bool
    -0.06
    .Direct
    -0.06
    arians
    -0.06
    CARD
    -0.06
    POSITIVE LOGITS
     Vera
    0.07
     использу
    0.07
     Secret
    0.07
    丶
    0.06
     Oswald
    0.06
     BuzzFeed
    0.06
     Μον
    0.06
     làn
    0.06
     Sayı
    0.06
     tăng
    0.06
    Act Density 0.030%

    No Known Activations