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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kontakt
    -0.07
     NSError
    -0.07
     Origins
    -0.07
     Nights
    -0.06
     Accounting
    -0.06
    �
    -0.06
    prefix
    -0.06
    غر
    -0.06
     bugs
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     sữa
    0.06
     *↵↵↵
    0.06
    ">'↵
    0.06
    .'</
    0.06
    _transform
    0.06
    +:
    0.06
     Ма
    0.06
     των
    0.06
    θεση
    0.06
     neben
    0.06
    Act Density 0.096%

    No Known Activations