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

    Neuronpedia

    INDEX
    Explanations

    nouns followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    1.05
    ει
    1.01
    ார்க
    0.94
    ক
    0.88
     aree
    0.86
     znacznie
    0.84
     ακόμα
    0.84
     musica
    0.81
    오는
    0.79
    녁
    0.79
    POSITIVE LOGITS
    it
    1.15
     evidences
    0.91
    beans
    0.90
    nama
    0.88
     commences
    0.87
    ᚄ
    0.85
    ja
    0.85
     диагности
    0.85
    creates
    0.84
    platz
    0.83
    Act Density 0.209%

    No Known Activations