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

    Neuronpedia

    INDEX
    Explanations

    experiences and encounters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    originally
    0.43
    uncur
    0.40
    downcase
    0.39
     ลด
    0.39
     Originally
    0.38
    ลด
    0.38
    wayne
    0.38
    carboxylic
    0.38
    Laugh
    0.38
    інки
    0.37
    POSITIVE LOGITS
     encountered
    0.53
     encounters
    0.52
     museums
    0.51
     comparison
    0.50
     airports
    0.50
    遇到的
    0.50
     rencontr
    0.49
    我在
    0.49
     encounter
    0.49
     توقع
    0.49
    Act Density 0.098%

    No Known Activations