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

    Neuronpedia

    INDEX
    Explanations

    mentioned languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supposition
    0.35
     contexto
    0.34
    勍
    0.33
     কিছুটা
    0.32
     исход
    0.32
    ﺗ
    0.32
    context
    0.32
    ásticas
    0.32
    纪
    0.31
     guise
    0.31
    POSITIVE LOGITS
     aforementioned
    0.50
     mencionados
    0.44
     mencionado
    0.42
     afore
    0.37
    上述
    0.35
     genannten
    0.33
    뿐
    0.33
     mentioned
    0.33
    Besides
    0.31
     altres
    0.31
    Act Density 0.216%

    No Known Activations