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

    Neuronpedia

    INDEX
    Explanations

    html heading tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Benefits
    0.45
     brunt
    0.40
     Successfully
    0.39
     Apo
    0.38
    臤
    0.36
     Benefit
    0.35
     Gradually
    0.34
     Deployment
    0.34
     Intel
    0.34
     Sees
    0.34
    POSITIVE LOGITS
    \$
    0.49
     hijas
    0.47
    imized
    0.47
     پری
    0.44
    ᐋ
    0.44
     ज
    0.43
     niveaux
    0.42
     mucha
    0.42
     związane
    0.42
     quarters
    0.42
    Act Density 0.024%

    No Known Activations