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

    Neuronpedia

    INDEX
    Explanations

    events and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (uri
    -0.07
    <source
    -0.07
    ์และ
    -0.06
     leaks
    -0.06
    [path
    -0.06
    ([[
    -0.06
    Systems
    -0.06
     onSave
    -0.06
    (email
    -0.06
    Here
    -0.06
    POSITIVE LOGITS
     society
    0.08
    do
    0.07
     japan
    0.07
     England
    0.07
    cher
    0.07
     puerto
    0.07
     Zimmerman
    0.06
    und
    0.06
     MAG
    0.06
     Guinea
    0.06
    Act Density 0.245%

    No Known Activations