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

    Neuronpedia

    INDEX
    Explanations

    border

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _routes
    -0.07
     margins
    -0.07
    353
    -0.07
     featured
    -0.07
    》的
    -0.07
     unanimous
    -0.07
     Approximately
    -0.06
     Upper
    -0.06
     majority
    -0.06
    .application
    -0.06
    POSITIVE LOGITS
    str
    0.07
    Vý
    0.06
     Billing
    0.06
     meget
    0.06
    BOX
    0.06
    (depth
    0.06
    园
    0.06
    REG
    0.06
     sik
    0.06
    Carl
    0.06
    Act Density 0.011%

    No Known Activations