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

    Neuronpedia

    INDEX
    Explanations

    intelligence assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yummy
    1.35
     lindos
    1.32
     veggies
    1.29
    --’
    1.27
     goodies
    1.24
    1.23
     gals
    1.21
     mooie
    1.19
    --“
    1.16
     meds
    1.15
    POSITIVE LOGITS
    ).[
    1.44
    ō
    1.42
    ,[
    1.37
    .[
    1.35
    ),[
    1.32
    )[
    1.27
    ".[
    1.26
     Encyclopædia
    1.26
     انھیں
    1.22
    <sup>
    1.21
    Act Density 0.618%

    No Known Activations