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

    Neuronpedia

    INDEX
    Explanations

    Canned food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রি
    0.97
     га
    0.86
    ري
    0.85
     produtt
    0.85
     chiamata
    0.84
    тур
    0.83
     sư
    0.82
    ARTER
    0.81
     Shill
    0.80
    ي
    0.80
    POSITIVE LOGITS
    liness
    1.02
    勿
    0.82
    ηση
    0.82
     NSError
    0.80
    ляции
    0.79
    ógica
    0.78
     Optimal
    0.76
    ”:
    0.73
    fetch
    0.72
    О
    0.71
    Act Density 0.001%

    No Known Activations