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

    Neuronpedia

    INDEX
    Explanations

    calculating amounts and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moeilijk
    0.44
     helfen
    0.39
     സ്റ്റ
    0.39
    ক্
    0.38
    vänd
    0.38
     carefully
    0.38
     simpler
    0.38
     नींद
    0.38
     homeomorphism
    0.37
     வீட்டு
    0.37
    POSITIVE LOGITS
    未來
    0.44
    ूद
    0.42
    未来
    0.41
     futura
    0.41
    <0xE3>
    0.38
     hivyo
    0.38
     has
    0.38
    在
    0.37
    竟然
    0.37
    Cuánto
    0.37
    Act Density 0.001%

    No Known Activations