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

    Neuronpedia

    INDEX
    Explanations

    Multimedia

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on occurrences of the word “multimedia.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ใบ
    -0.07
    енка
    -0.07
    IAS
    -0.07
     женщины
    -0.07
    adies
    -0.07
     대한
    -0.07
     가족
    -0.07
    _ROOT
    -0.06
     whistle
    -0.06
     Republican
    -0.06
    POSITIVE LOGITS
     Multimedia
    0.10
     middleware
    0.08
    BUFF
    0.07
     multimedia
    0.07
    imedia
    0.07
    fram
    0.07
    .randomUUID
    0.07
    ферен
    0.07
    vv
    0.07
    nev
    0.07
    Act Density 0.003%

    No Known Activations