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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    code examples related to data handling and manipulation in Python.

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

    It activates on the phrase “descriptive answer for” in the system instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ein
    -0.07
    Pinterest
    -0.07
     цього
    -0.06
    -left
    -0.06
    _partial
    -0.06
    jualan
    -0.06
     від
    -0.06
     sollte
    -0.06
    leveland
    -0.06
    定的
    -0.06
    POSITIVE LOGITS
    Staff
    0.07
     Trucks
    0.07
     migrants
    0.07
     artículo
    0.06
    之间
    0.06
     Aware
    0.06
     éxito
    0.06
     Careers
    0.06
     маш
    0.06
     vũ
    0.06
    Act Density 0.004%

    No Known Activations