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

    Neuronpedia

    INDEX
    Explanations

    Your Name or credential holder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FAQs
    0.83
     gle
    0.74
     raises
    0.68
     concepts
    0.67
    ently
    0.67
     treats
    0.67
     raised
    0.66
     items
    0.66
     instructions
    0.65
     treatments
    0.65
    POSITIVE LOGITS
    Your
    1.18
    Usuario
    1.13
    YOUR
    1.12
    David
    1.11
    Michael
    1.08
    Robert
    1.07
    Miguel
    1.05
    Josh
    1.03
    UserName
    1.02
    你的
    1.01
    Act Density 0.338%

    No Known Activations