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

    Neuronpedia

    INDEX
    Explanations

    Brackets and parentheses

    np_max-act · gemini-2.0-flash

    The neuron spotlights multi‐value assignment statements that include an error return (i.e. “…, err := …”)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lyr
    -0.07
     IList
    -0.06
     rational
    -0.06
    gateway
    -0.06
     Buster
    -0.06
    laughter
    -0.06
     الثالث
    -0.06
     NV
    -0.06
    んです
    -0.06
     Malk
    -0.06
    POSITIVE LOGITS
     sebe
    0.07
     dissolution
    0.07
     تماس
    0.07
     "../
    0.07
     เจ
    0.06
    PCA
    0.06
    |
    0.06
    _listen
    0.06
    =>'
    0.06
    $i
    0.06
    Act Density 0.029%

    No Known Activations