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

    Neuronpedia

    INDEX
    Explanations

    list items with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     није
    0.44
     Stories
    0.44
     Allocated
    0.43
     schoolchildren
    0.43
     wheeled
    0.43
     Coaches
    0.43
    一张
    0.43
    cards
    0.42
     Leng
    0.42
     pseudos
    0.42
    POSITIVE LOGITS
     reikia
    0.48
     만드는
    0.42
     extraer
    0.41
     примеру
    0.41
     collecte
    0.40
     peuvent
    0.40
     foreclose
    0.40
     pouvons
    0.39
     chahiye
    0.39
    formin
    0.38
    Act Density 0.002%

    No Known Activations