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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash

    The neuron never activates on any of the code or text—it appears to be essentially “dead” and does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gol
    -0.07
     continu
    -0.07
    ():↵
    -0.07
    置
    -0.06
    -packages
    -0.06
    欢
    -0.06
     Thompson
    -0.06
    acent
    -0.06
    麗
    -0.06
    tığını
    -0.06
    POSITIVE LOGITS
     resorts
    0.07
    ór
    0.06
     safeguard
    0.06
    (skb
    0.06
     affid
    0.06
    478
    0.06
    -Jun
    0.06
     захоп
    0.06
     pharmaceutical
    0.05
    Curve
    0.05
    Act Density 0.005%

    No Known Activations