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

    Neuronpedia

    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toc
    -0.07
    카지노
    -0.07
    ề
    -0.07
     вимог
    -0.06
    "]]
    -0.06
    _SERVER
    -0.06
     Pokémon
    -0.06
     dan
    -0.06
     аб
    -0.06
    probably
    -0.06
    POSITIVE LOGITS
    되었
    0.07
     Stay
    0.06
    HasColumnName
    0.06
     پیچ
    0.06
     alanda
    0.06
    ↵      ↵
    0.06
    stay
    0.06
    炮
    0.06
    _tooltip
    0.06
     greatness
    0.06
    Act Density 0.008%

    No Known Activations