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

    Neuronpedia

    INDEX
    Explanations

    OAuth, Unreal, T-cells, SARS, Lingnan, Mauritius

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🧒
    0.38
    MANAGER
    0.37
    漀
    0.37
     এমনই
    0.36
    ♧
    0.35
    PYTHON
    0.34
    🐤
    0.34
    કના
    0.34
    在该
    0.33
    了他的
    0.33
    POSITIVE LOGITS
     Tukey
    0.33
     Mathematica
    0.31
     Magento
    0.31
     G
    0.30
     Mr
    0.30
     Wikipedia
    0.30
     Shopify
    0.30
     hashlib
    0.30
     K
    0.30
     Bob
    0.30
    Act Density 0.345%

    No Known Activations