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

    Neuronpedia

    INDEX
    Explanations

    government programs and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     statewide
    0.44
     Canadian
    0.43
     Совет
    0.41
     cordon
    0.41
     provinces
    0.40
     canadian
    0.40
     Canadá
    0.39
     Canadi
    0.39
     canadien
    0.39
     gubern
    0.39
    POSITIVE LOGITS
     Ezekiel
    0.48
    lore
    0.44
    Study
    0.41
    Ez
    0.41
    Pay
    0.40
     Testament
    0.40
    Simpson
    0.40
    splitting
    0.40
     satt
    0.39
     hardening
    0.39
    Act Density 0.002%

    No Known Activations