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

    Neuronpedia

    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “lead” (especially “leads” or “lead frame”) in semiconductor packaging descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Buscar
    -0.07
    _detector
    -0.07
    Ger
    -0.07
    ]);
↵
↵
    -0.07
     leur
    -0.07
     rapp
    -0.06
    Agregar
    -0.06
    bufio
    -0.06
    (grammarAccess
    -0.06
    kud
    -0.06
    POSITIVE LOGITS
    平方
    0.07
    /star
    0.07
     інш
    0.07
    لية
    0.06
    rors
    0.06
    ็อต
    0.06
    deen
    0.06
    ﺪ
    0.06
     ใช
    0.06
    -output
    0.06
    Act Density 0.006%

    No Known Activations