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

    Neuronpedia

    INDEX
    Explanations

    religious or programming lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wines
    1.02
     Acres
    0.84
     Oils
    0.83
     Skins
    0.81
     Arms
    0.81
     Fish
    0.80
     ナイロン
    0.79
    小麦
    0.78
    一个
    0.77
     Drill
    0.77
    POSITIVE LOGITS
     whatnot
    1.15
     therefore
    1.00
    orra
    0.97
    ść
    0.96
    therefore
    0.93
     somit
    0.92
    諧
    0.92
    romeda
    0.90
    rogens
    0.89
    tfidf
    0.89
    Act Density 0.001%

    No Known Activations