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

    Neuronpedia

    INDEX
    Explanations

    questions and requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     також
    -0.07
     Когда
    -0.07
     Bonnie
    -0.07
     beverages
    -0.07
     через
    -0.07
     battle
    -0.07
     необхідно
    -0.06
     palabras
    -0.06
     leveraging
    -0.06
     banco
    -0.06
    POSITIVE LOGITS
     incidence
    0.07
     yog
    0.06
    vented
    0.06
     dob
    0.06
    (INFO
    0.06
     interruption
    0.06
    .mode
    0.06
    Pour
    0.06
     redevelopment
    0.06
     analytic
    0.06
    Act Density 0.118%

    No Known Activations