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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects the appearance of appellate court header phrases (e.g. “IN THE COURT OF APPEAL OF …”) in judicial opinions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oco
    -0.07
    ennon
    -0.07
    Signals
    -0.07
     облі
    -0.06
     Nero
    -0.06
    ไทย
    -0.06
     나를
    -0.06
    ีพ
    -0.06
     nen
    -0.06
     confuse
    -0.06
    POSITIVE LOGITS
     이번
    0.07
     Gear
    0.06
    。此
    0.06
    _spell
    0.06
     president
    0.06
    sak
    0.06
    <decltype
    0.06
     seis
    0.06
     pev
    0.06
    everything
    0.06
    Act Density 0.001%

    No Known Activations