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

    Neuronpedia

    INDEX
    Explanations

    decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ழி
    0.42
    Z
    0.40
     আর
    0.39
    ğiniz
    0.38
    Aligned
    0.38
    铌
    0.38
    軫
    0.37
     pinion
    0.36
    ისა
    0.36
     মধ্যকার
    0.35
    POSITIVE LOGITS
    assade
    0.42
    ierls
    0.40
    Edward
    0.39
    ترل
    0.39
     शास्त्र
    0.38
     स्टैट
    0.37
    estimators
    0.37
    𝑬
    0.36
    iennes
    0.36
    lEdit
    0.36
    Act Density 0.015%

    No Known Activations