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

    Neuronpedia

    INDEX
    Explanations

    don't do or think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نقص
    1.03
    ΐ
    1.00
    renia
    0.96
     ail
    0.96
    而已
    0.89
    Н
    0.87
    phonon
    0.87
     nursery
    0.87
    PDF
    0.86
    कर
    0.86
    POSITIVE LOGITS
     جوړونکی
    1.19
     noun
    1.16
     вопло
    1.12
    crafted
    1.11
    apatillas
    1.09
    drawable
    1.05
     والے
    1.05
    ्यात
    1.03
    ли
    1.03
    planner
    1.02
    Act Density 0.000%

    No Known Activations