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

    Neuronpedia

    INDEX
    Explanations

    reimburse

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting occurrences of reimbursement-related terms (e.g., “reimburse,” “reimbursement,” “reimbursed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cycle
    -0.07
    ipelines
    -0.06
    dq
    -0.06
     Act
    -0.06
     cycle
    -0.06
     पत
    -0.06
     Akron
    -0.06
    /connect
    -0.06
    (wp
    -0.06
    KeyEvent
    -0.06
    POSITIVE LOGITS
     reimburse
    0.10
     reimb
    0.10
     reimbursement
    0.09
    bursement
    0.08
    [R
    0.07
     orm
    0.07
    ioxid
    0.07
    Blur
    0.07
     Dear
    0.06
    .isConnected
    0.06
    Act Density 0.002%

    No Known Activations