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

    Neuronpedia

    INDEX
    Explanations

    rotation, fermentation, hydration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.68
    I
    0.68
    И
    0.65
    あまり
    0.58
    nae
    0.58
    ።
    0.57
    ama
    0.56
    net
    0.55
    inę
    0.54
    し
    0.54
    POSITIVE LOGITS
    та
    0.89
    ت
    0.63
    त
    0.63
     systém
    0.61
     bacterias
    0.61
     HAS
    0.61
    การ
    0.59
     on
    0.58
    ே
    0.58
     spezi
    0.58
    Act Density 0.058%

    No Known Activations