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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron activates on the term “permission” in open-source license boilerplate headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     пр
    -0.08
     dictate
    -0.06
    显
    -0.06
    udge
    -0.06
    -python
    -0.06
    lä
    -0.06
     wonderfully
    -0.05
     Asus
    -0.05
     méně
    -0.05
    fection
    -0.05
    POSITIVE LOGITS
     Porn
    0.07
     Nvidia
    0.07
     "')
    0.07
    aaaa
    0.06
    ี.
    0.06
     ding
    0.06
    월까지
    0.06
    aska
    0.06
     '}
    0.06
    vidia
    0.06
    Act Density 0.001%

    No Known Activations