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

    Neuronpedia

    INDEX
    Explanations

    dates and official records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    láš
    -0.07
    .Total
    -0.07
    =T
    -0.06
     Rows
    -0.06
    Planning
    -0.06
    -summary
    -0.06
    orld
    -0.06
     Gio
    -0.06
     رسید
    -0.06
    Ask
    -0.06
    POSITIVE LOGITS
    WARN
    0.07
    ()?;↵
    0.06
    |,↵
    0.06
    官网
    0.06
    enment
    0.06
    ],
↵
    0.06
    warn
    0.06
    џџџ
    0.06
    principal
    0.06
     فبراير
    0.06
    Act Density 0.017%

    No Known Activations