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

    Neuronpedia

    INDEX
    Explanations

    beginning

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect references to specific historical time periods and associated place or event names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traffic
    -0.07
    ans
    -0.06
    (**
    -0.06
     gods
    -0.06
     politics
    -0.06
     protest
    -0.06
     project
    -0.06
    _inode
    -0.06
     butto
    -0.06
    Pager
    -0.06
    POSITIVE LOGITS
     sitesinde
    0.07
     وغير
    0.07
    ConfigurationException
    0.07
    acion
    0.06
     أبريل
    0.06
     đ
    0.06
     astonishing
    0.06
    در
    0.06
    _bg
    0.06
                    ↵
    0.06
    Act Density 0.089%

    No Known Activations