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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Validation
    -0.07
    '})↵
    -0.06
    Iraq
    -0.06
    ?>">↵
    -0.06
    ']];↵
    -0.06
    ektör
    -0.06
     chod
    -0.06
     avez
    -0.06
     Tập
    -0.06
    rightarrow
    -0.06
    POSITIVE LOGITS
     serr
    0.07
     خورد
    0.07
    leased
    0.07
    00
    0.06
    (aa
    0.06
    [source
    0.06
     taxpayer
    0.06
    やる夫
    0.06
    ají
    0.06
     меш
    0.06
    Act Density 0.003%

    No Known Activations