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

    Neuronpedia

    INDEX
    Explanations

    reviewed

    np_max-act · gemini-2.0-flash

    This neuron spotlights the routine, boilerplate judicial‐opinion phrases indicating the court’s review of the record (e.g. “We have carefully reviewed the record and find no reversible error”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bent
    -0.08
     holiday
    -0.06
    क
    -0.06
    amak
    -0.06
     heg
    -0.06
    lad
    -0.06
     alright
    -0.06
     bohat
    -0.06
    errorMsg
    -0.06
     Apex
    -0.06
    POSITIVE LOGITS
     Except
    0.07
    Except
    0.06
    _FP
    0.06
    둘
    0.06
     capitalize
    0.06
    projectId
    0.06
     *,↵
    0.06
    ..<
    0.06
     sift
    0.06
     gà
    0.06
    Act Density 0.004%

    No Known Activations