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

    Neuronpedia

    INDEX
    Explanations

    abstract

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by occurrences of the keyword “abstract.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Photo
    -0.08
     controlled
    -0.07
    Signal
    -0.07
    εξ
    -0.06
     logarith
    -0.06
    OUT
    -0.06
     evening
    -0.06
     voluntary
    -0.06
     sending
    -0.06
    ind
    -0.06
    POSITIVE LOGITS
     тверд
    0.07
     本
    0.07
     fundament
    0.07
     บาท
    0.06
     atm
    0.06
     Consulting
    0.06
    Unc
    0.06
     completamente
    0.06
    .mj
    0.06
    μεν
    0.06
    Act Density 0.003%

    No Known Activations