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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    This neuron detects inline legal‐citation signals (e.g. “see,” “see also,” etc.) that introduce case‐law or statutory references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Franç
    -0.06
    frey
    -0.06
    たく
    -0.06
    ，全
    -0.06
     KeyError
    -0.06
    Rh
    -0.06
    lüğ
    -0.06
    mıyor
    -0.06
     pound
    -0.06
     thous
    -0.06
    POSITIVE LOGITS
    isha
    0.07
    .node
    0.07
    iedy
    0.07
     Wrath
    0.07
     AppRoutingModule
    0.06
     breaches
    0.06
    malar
    0.06
     wired
    0.06
     crafted
    0.06
     القرن
    0.06
    Act Density 0.001%

    No Known Activations