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

    Neuronpedia

    INDEX
    Explanations

    expensive / increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    童
    0.44
    GAME
    0.43
    <0x10>
    0.41
    四大
    0.41
    ô
    0.41
     visionary
    0.40
    hô
    0.40
    Vide
    0.40
     पोलियो
    0.40
    闹
    0.39
    POSITIVE LOGITS
     महंगे
    0.48
     Ł
    0.47
     Improves
    0.41
    ಂಡ್
    0.41
     increases
    0.40
     Increases
    0.40
     Hypothesis
    0.40
     ইংল্যান্ড
    0.40
     expensive
    0.40
     Increased
    0.40
    Act Density 0.016%

    No Known Activations