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

    Neuronpedia

    INDEX
    Explanations

    lemon

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wolf
    0.73
    wolves
    0.70
     wolf
    0.69
    Bry
    0.69
    Wing
    0.68
     barns
    0.64
     Wolf
    0.64
    Village
    0.63
    Wolf
    0.63
    เง
    0.63
    POSITIVE LOGITS
    🍋
    1.55
     citrus
    1.52
     juice
    1.49
    Cit
    1.47
    cit
    1.40
     Citrus
    1.38
     Cit
    1.34
     lemons
    1.34
    柠檬
    1.34
     lemon
    1.33
    Act Density 0.013%

    No Known Activations