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

    Neuronpedia

    INDEX
    Explanations

    Patents

    np_max-act · gemini-2.0-flash

    This neuron detects patent citation references (e.g. “U.S. Pat. No. 4,653,911”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    decltype
    -0.06
    ();
↵
↵
    -0.06
    شود
    -0.06
    廳
    -0.06
    ########################################################################
    -0.06
    tik
    -0.06
    lerden
    -0.06
    非
    -0.06
     ();↵↵
    -0.06
    ()));↵
    -0.06
    POSITIVE LOGITS
    änder
    0.07
     Ober
    0.06
    .／
    0.06
    抓
    0.06
    (phone
    0.06
    革
    0.06
     eliminar
    0.06
    _mentions
    0.06
     slack
    0.06
    AtPath
    0.06
    Act Density 0.028%

    No Known Activations