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

    Neuronpedia

    INDEX
    Explanations

    Legal and historical texts

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on terms referring to formal legislative procedures and record‐keeping (e.g. “met,” “houses,” “assembly,” “voted,” “record,” “journals,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     skips
    -0.06
    one
    -0.06
     Inflate
    -0.06
    inction
    -0.06
     jumps
    -0.06
    hu
    -0.06
    Ģ
    -0.06
    Xml
    -0.06
    .»
    -0.06
    ���
    -0.06
    POSITIVE LOGITS
     Blogger
    0.07
     entityId
    0.07
     Plugins
    0.07
     tls
    0.07
     Nature
    0.06
     SimpleDateFormat
    0.06
    TestClass
    0.06
     nosso
    0.06
    aba
    0.06
    raries
    0.06
    Act Density 0.001%

    No Known Activations