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

    Neuronpedia

    INDEX
    Explanations

    ized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plans
    -0.08
     contém
    -0.08
     arquivos
    -0.08
     종류
    -0.08
    Needed
    -0.08
     Songs
    -0.07
    ालय
    -0.07
     Branche
    -0.07
     Congreg
    -0.07
     대해서
    -0.07
    POSITIVE LOGITS
     exaggerated
    0.10
     exagger
    0.10
    �
    0.09
     للغاية
    0.09
    மான
    0.08
     exager
    0.08
     redesigned
    0.08
     بالا
    0.07
     Valentin
    0.07
    мал
    0.07
    Act Density 0.005%

    No Known Activations