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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash

    This neuron activates on the names of specification headings in a numbered list (e.g. “Printing Speed,” “Materials,” “Industrial printers,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     StatusBar
    -0.06
     cosplay
    -0.06
     Hip
    -0.06
    战
    -0.06
    >Your
    -0.06
    سنگ
    -0.06
    �
    -0.06
     Nun
    -0.06
    appable
    -0.06
     Flower
    -0.06
    POSITIVE LOGITS
    ladı
    0.07
    _passwd
    0.06
    ()==
    0.06
    $↵
    0.06
     erotico
    0.06
     hollow
    0.06
    .setParent
    0.06
    Steve
    0.06
    รด
    0.06
     plumbing
    0.06
    Act Density 0.158%

    No Known Activations