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

    Neuronpedia

    INDEX
    Explanations

    trillion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     millions
    1.23
     million
    1.19
    Million
    1.12
     milion
    1.03
     Million
    1.02
     milioni
    1.01
     Millions
    1.00
    Millions
    1.00
     millones
    0.96
    million
    0.95
    POSITIVE LOGITS
     pet
    1.61
     Pet
    1.60
    pet
    1.40
    Pet
    1.40
     PET
    1.21
    PET
    1.20
     Pets
    1.18
     ter
    1.14
     pets
    1.12
     ペット
    1.09
    Act Density 0.051%

    No Known Activations