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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash

    mentions of financial transactions and economic conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on personal pronouns (e.g., I, we, he, she, it, they) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nord
    -0.07
    ild
    -0.06
     pis
    -0.06
     наруш
    -0.06
     riff
    -0.06
     Privacy
    -0.06
     turb
    -0.06
     On
    -0.06
    kami
    -0.06
     Et
    -0.06
    POSITIVE LOGITS
    GetPosition
    0.07
    ):(
    0.06
     годы
    0.06
    _CHARACTER
    0.06
     JOptionPane
    0.06
    	glm
    0.06
    سون
    0.06
    .'),↵
    0.06
    aneous
    0.06
    Ordered
    0.06
    Act Density 0.004%

    No Known Activations