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

    Neuronpedia

    INDEX
    Explanations

    /a

    np_max-act · gemini-2.0-flash

    This neuron detects “d/b/a” (doing business as) style abbreviations indicating alternate business names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    GP
    -0.06
    (Char
    -0.06
     Uh
    -0.06
    pert
    -0.06
    _aa
    -0.06
    Fair
    -0.06
     Pale
    -0.06
    .setUp
    -0.06
    licer
    -0.06
     رسمی
    -0.06
    POSITIVE LOGITS
    itez
    0.07
    еи
    0.06
     Sally
    0.06
    encing
    0.06
     Nowadays
    0.06
    调
    0.06
     inspir
    0.06
     predominant
    0.06
    .proxy
    0.06
    atten
    0.06
    Act Density 0.003%

    No Known Activations