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

    Neuronpedia

    INDEX
    Explanations

    asking alternatives with "or"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denen
    0.36
     collects
    0.34
    Collect
    0.33
    ന്ന്
    0.33
    Compute
    0.33
     البته
    0.32
    kari
    0.32
    Check
    0.32
    Google
    0.32
    案
    0.32
    POSITIVE LOGITS
     did
    1.23
    Does
    1.13
     does
    1.11
     Does
    1.09
     Did
    1.09
    Did
    1.05
    did
    1.02
    does
    0.99
     do
    0.97
     Are
    0.96
    Act Density 0.014%

    No Known Activations