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

    Neuronpedia

    INDEX
    Explanations

    outgoing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Base
    -0.07
     τελ
    -0.07
    olia
    -0.06
    ória
    -0.06
    eyn
    -0.06
    ox
    -0.06
    acs
    -0.06
    oric
    -0.06
     Explorer
    -0.06
     Subcommittee
    -0.06
    POSITIVE LOGITS
     outgoing
    0.11
    .people
    0.07
    (active
    0.07
     accessibility
    0.06
     debts
    0.06
    kim
    0.06
    jspb
    0.06
     warmly
    0.06
    }/#{
    0.06
    /categories
    0.06
    Act Density 0.011%

    No Known Activations