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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ň
    -0.07
    django
    -0.06
     beams
    -0.06
    $lang
    -0.06
    !".
    -0.06
     elong
    -0.06
     kwargs
    -0.06
     жар
    -0.06
    .RequestBody
    -0.06
    ?");↵
    -0.06
    POSITIVE LOGITS
    Prem
    0.06
    zyć
    0.06
    Benefits
    0.06
    LOUR
    0.06
    ANGUAGE
    0.06
     vets
    0.06
    uitive
    0.06
     ait
    0.06
    Fore
    0.06
     seams
    0.06
    Act Density 0.013%

    No Known Activations