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

    Neuronpedia

    INDEX
    Explanations

    agreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dolar
    -0.07
     Driver
    -0.07
    RefCount
    -0.06
     heel
    -0.06
     dungeons
    -0.06
    UserData
    -0.06
     chocol
    -0.06
    '*
    -0.06
     rats
    -0.06
     UsersController
    -0.06
    POSITIVE LOGITS
     Agreement
    0.10
     treaty
    0.08
     agreement
    0.08
    reements
    0.08
     pact
    0.07
     Covenant
    0.07
     agreements
    0.07
     Pact
    0.07
     treaties
    0.07
     covenant
    0.07
    Act Density 0.022%

    No Known Activations