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

    Neuronpedia

    INDEX
    Explanations

    percentages and percents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trading
    0.40
    protection
    0.39
    production
    0.39
    prisoners
    0.38
    কেরা
    0.37
     countrymen
    0.37
    দিনী
    0.37
    tax
    0.36
     zuf
    0.36
    Conservation
    0.36
    POSITIVE LOGITS
     &
    0.38
     Tempor
    0.38
     SDN
    0.38
     Tea
    0.37
     Tener
    0.37
     và
    0.37
    NullException
    0.37
     garn
    0.36
     Replace
    0.36
     Sánchez
    0.36
    Act Density 0.003%

    No Known Activations