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

    Neuronpedia

    INDEX
    Explanations

    code snippets/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )return
    -0.07
    ธาน
    -0.06
     INTERRU
    -0.06
    Suppress
    -0.06
     mey
    -0.06
    Ph
    -0.06
     miser
    -0.06
    ısır
    -0.06
     kayb
    -0.06
     navy
    -0.06
    POSITIVE LOGITS
     workload
    0.07
    Refer
    0.07
               ↵
    0.07
     "").
    0.06
    Servers
    0.06
    ليزية
    0.06
     bicycles
    0.06
    391
    0.06
     loose
    0.06
     offices
    0.06
    Act Density 0.000%

    No Known Activations