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

    Neuronpedia

    INDEX
    Explanations

    Software compilation/building

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of building or compiling software (e.g. words like “compile,” “built,” “building”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ộc
    -0.07
    (My
    -0.06
    ike
    -0.06
     Doyle
    -0.06
    도를
    -0.06
    -function
    -0.06
    adro
    -0.06
    olist
    -0.06
    (stock
    -0.06
    loomberg
    -0.06
    POSITIVE LOGITS
     NAME
    0.06
     С
    0.06
     तस
    0.06
    (api
    0.06
    subscribe
    0.06
     =
↵
    0.06
     Ian
    0.06
     depr
    0.06
     segue
    0.06
    .�
    0.06
    Act Density 0.021%

    No Known Activations