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

    Neuronpedia

    INDEX
    Explanations

    objective and rhymes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    การ
    0.46
    雁
    0.46
    ก
    0.45
    к
    0.45
     rambling
    0.43
    ด
    0.43
    スピ
    0.42
    itious
    0.42
    ,
    0.42
    _
    0.41
    POSITIVE LOGITS
     projetos
    0.45
     nossas
    0.42
     numerosas
    0.41
     Projekte
    0.40
    ட்டுகள்
    0.40
    ńskiej
    0.40
     painstakingly
    0.40
     projektu
    0.39
    ggen
    0.39
     پروژه
    0.39
    Act Density 0.004%

    No Known Activations