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

    Neuronpedia

    INDEX
    Explanations

    measurements and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omite
    -0.07
    heavy
    -0.06
    pheric
    -0.06
    /sites
    -0.06
    یس
    -0.06
    BODY
    -0.06
    transactions
    -0.06
    specified
    -0.06
     txn
    -0.06
    ']:↵
    -0.06
    POSITIVE LOGITS
     oppression
    0.07
     creating
    0.06
     Deferred
    0.06
    _FLAG
    0.06
     clientes
    0.06
     capitalized
    0.06
     yeah
    0.06
     innocence
    0.06
     potentially
    0.06
     history
    0.06
    Act Density 0.079%

    No Known Activations