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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    The neuron activates on programming‐language import statements, marking the beginnings of import lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pot
    -0.07
     Quick
    -0.07
    PWD
    -0.07
     desk
    -0.07
     Fulton
    -0.06
     Microsoft
    -0.06
     全
    -0.06
    Miss
    -0.06
     هوش
    -0.06
    .Method
    -0.06
    POSITIVE LOGITS
     مرة
    0.06
    edata
    0.06
    μιλος
    0.06
    anne
    0.06
     chars
    0.06
     vivastreet
    0.06
    иты
    0.06
     setState
    0.06
    추천
    0.06
     limburg
    0.06
    Act Density 0.025%

    No Known Activations