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

    Neuronpedia

    INDEX
    Explanations

    retirement plans

    np_max-act · gemini-2.0-flash

    The neuron detects formal references to pension or employee benefit plans (e.g., “Pension Fund,” “Plan,” “Trustees,” “ERISA”) in legal text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    цій
    -0.08
     Burb
    -0.07
     Iso
    -0.06
    aln
    -0.06
    Buying
    -0.06
    oron
    -0.06
     font
    -0.06
    .id
    -0.06
     flop
    -0.06
     прос
    -0.06
    POSITIVE LOGITS
    (=
    0.07
     jog
    0.06
     Sanat
    0.06
    :CGPoint
    0.06
    creat
    0.06
    Southern
    0.06
    とした
    0.06
    층의
    0.06
    ्ययन
    0.06
     ศร
    0.06
    Act Density 0.006%

    No Known Activations