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

    Neuronpedia

    INDEX
    Explanations

    ORDER

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find section‐heading labels in judicial opinions (e.g. “ORDER,” “JUDGMENT”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Avengers
    -0.07
     Free
    -0.07
    YSQL
    -0.07
    風
    -0.06
    .Inf
    -0.06
     hưởng
    -0.06
    _ask
    -0.06
     webs
    -0.06
     Cathedral
    -0.06
     Url
    -0.06
    POSITIVE LOGITS
    )["
    0.07
     حکم
    0.07
    ostat
    0.06
     Beitrag
    0.06
     agreg
    0.06
     enclave
    0.06
     hroz
    0.06
    -encoded
    0.06
     велик
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations