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

    Neuronpedia

    INDEX
    Explanations

    arbitration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cols
    -0.07
     πολ
    -0.07
    (records
    -0.07
    温度
    -0.07
     SHOW
    -0.06
     infection
    -0.06
    .FullName
    -0.06
     :\
    -0.06
    "W
    -0.06
    .Pull
    -0.06
    POSITIVE LOGITS
     arbitration
    0.14
     arbit
    0.12
     Arbit
    0.11
     arbitr
    0.10
     Arb
    0.08
     arb
    0.08
     ump
    0.07
    Compet
    0.07
    bbie
    0.06
     Arabic
    0.06
    Act Density 0.003%

    No Known Activations