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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is attuned to German words (especially longer, compound or derived forms) built on the “-ieren” suffix (e.g. participles like “unzensierten” or infinitives like “reifen”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inize
    -0.07
    imizeBox
    -0.07
    rians
    -0.07
    iParam
    -0.06
     Walk
    -0.06
    oring
    -0.06
    itory
    -0.06
    ımıza
    -0.06
     drowning
    -0.06
    (by
    -0.06
    POSITIVE LOGITS
    .InnerText
    0.07
    ",[
    0.07
     kontakt
    0.07
    	V
    0.07
     textStyle
    0.07
     brewery
    0.07
    +=(
    0.07
     nové
    0.06
     `,↵
    0.06
     Nachricht
    0.06
    Act Density 0.002%

    No Known Activations