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

    Neuronpedia

    INDEX
    Explanations

    importance or likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    자와
    0.57
    사와
    0.47
     आणि
    0.47
     மற்றும்
    0.45
    했고
    0.45
     및
    0.44
    기와
    0.44
     chibi
    0.44
     Tiểu
    0.44
     سایټ
    0.44
    POSITIVE LOGITS
     важли
    0.49
      
    0.47
    0.46
     vigt
    0.45
     important
    0.44
    ITION
    0.44
     crucial
    0.44
     importanti
    0.44
     blended
    0.43
    ingredients
    0.41
    Act Density 0.015%

    No Known Activations