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

    Neuronpedia

    INDEX
    Explanations

    scientific and conceptual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jewish
    0.46
    ZV
    0.46
    ZZ
    0.46
    Brien
    0.44
    ERC
    0.44
     wale
    0.44
    ｬ
    0.44
    Watts
    0.43
    You
    0.43
    JA
    0.43
    POSITIVE LOGITS
     attaqu
    0.44
    acées
    0.43
    çou
    0.43
     kaliteli
    0.43
    循
    0.43
    为
    0.43
     améliorer
    0.42
    కొ
    0.41
    背包
    0.41
    熟
    0.41
    Act Density 0.001%

    No Known Activations