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

    Neuronpedia

    INDEX
    Explanations

    brief

    np_max-act · gemini-2.0-flash

    This neuron activates on words in the “with … on the brief(s) were” attorney-at-briefs attribution lines in court opinions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    属于
    -0.08
    opolitan
    -0.07
     беременности
    -0.07
     세상
    -0.07
    ()).
    -0.07
     quanto
    -0.06
    typescript
    -0.06
    kı
    -0.06
    urovision
    -0.06
    019
    -0.06
    POSITIVE LOGITS
     Expense
    0.06
    .DateField
    0.06
    VIP
    0.06
     charcoal
    0.06
    achment
    0.06
    _INCLUDE
    0.06
    ds
    0.06
     dbname
    0.06
     rtc
    0.06
    resh
    0.06
    Act Density 0.001%

    No Known Activations