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

    Neuronpedia

    INDEX
    Explanations

    intervention and testing practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を実現
    0.49
    gazebo
    0.43
    женер
    0.42
     optimizes
    0.42
     تنس
    0.42
     சுற்றுச்சூழல்
    0.42
     زيت
    0.42
    నర్
    0.41
    িল্লী
    0.41
     lasts
    0.40
    POSITIVE LOGITS
     અને
    0.57
     याबाबत
    0.52
     आणि
    0.50
    पणे
    0.50
     và
    0.49
     Plea
    0.48
     and
    0.47
     اہم
    0.47
     Regarding
    0.47
     और
    0.46
    Act Density 0.002%

    No Known Activations