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

    Neuronpedia

    INDEX
    Explanations

    carbonate

    np_max-act · gemini-2.0-flash

    The neuron activates on chemical compound names ending in “-ide” or “-ate,” flagging terms like “oxide” and “carbonate.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Column
    -0.07
    .xaml
    -0.06
    .Download
    -0.06
    +","+
    -0.06
     Slayer
    -0.06
     possessions
    -0.06
    ){
↵
↵
    -0.06
    Sun
    -0.06
     JNI
    -0.06
    ,E
    -0.06
    POSITIVE LOGITS
     accommodating
    0.08
    ulates
    0.07
    obbled
    0.07
     carbonate
    0.07
    ा।
    0.07
     contributing
    0.07
    塔
    0.07
     jeszcze
    0.07
    acman
    0.07
    great
    0.07
    Act Density 0.003%

    No Known Activations