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

    Neuronpedia

    INDEX
    Explanations

    polymorphism Allocation Formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resisted
    0.45
     harshly
    0.45
    spun
    0.45
     considér
    0.43
     keenly
    0.43
    ou
    0.43
    ↷
    0.43
     resistentes
    0.42
     spared
    0.42
    members
    0.41
    POSITIVE LOGITS
     polymorphism
    0.44
     дизайн
    0.42
    াকিং
    0.42
    齧
    0.42
     Allocation
    0.42
    ナス
    0.42
     jinak
    0.42
     object
    0.41
     mye
    0.41
     Formatting
    0.41
    Act Density 0.008%

    No Known Activations