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

    Neuronpedia

    INDEX
    Explanations

    rearrangement

    np_max-act · gemini-2.0-flash

    This neuron activates on technical terms describing immune-receptor gene rearrangement and editing processes (e.g. V(D)J recombination, receptor editing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Anything
    -0.07
    clients
    -0.06
    hlen
    -0.06
     gossip
    -0.06
     Ending
    -0.06
    ，但是
    -0.06
     Burb
    -0.06
    Lic
    -0.06
    zos
    -0.06
    ISE
    -0.06
    POSITIVE LOGITS
     unlocking
    0.06
     supplementary
    0.06
     risk
    0.06
    ":"","
    0.06
    fine
    0.06
     inflated
    0.06
     arrived
    0.06
    един
    0.06
    (DIR
    0.06
    を行
    0.06
    Act Density 0.005%

    No Known Activations