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

    Neuronpedia

    INDEX
    Explanations

    Because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myös
    0.83
     Gemeins
    0.80
     unor
    0.79
     również
    0.78
     materia
    0.76
     tekst
    0.76
     materiaal
    0.74
     opet
    0.74
     Fahrzeug
    0.73
    0.73
    POSITIVE LOGITS
    ta
    0.86
    𝐠
    0.85
    上帝
    0.82
    av
    0.81
    am
    0.80
    ਜ਼
    0.80
     који
    0.79
    ziest
    0.79
    ác
    0.77
    getType
    0.77
    Act Density 0.030%

    No Known Activations