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

    Neuronpedia

    INDEX
    Explanations

    and then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.24
    ↵↵
    0.23
     &
    0.21
    ))
    0.21
     -->
    0.19
     ayaa
    0.19
          
    0.19
             
    0.18
    :
    0.18
    Diameter
    0.18
    POSITIVE LOGITS
     frankly
    0.33
     luckily
    0.30
     thankfully
    0.29
     it
    0.28
     fortunately
    0.27
     why
    0.27
     Frankly
    0.27
     there
    0.26
    それは
    0.25
     rightly
    0.25
    Act Density 0.067%

    No Known Activations