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

    Neuronpedia

    INDEX
    Explanations

    related to context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ட்
    0.40
     visualizar
    0.39
    独自の
    0.38
     expresión
    0.38
    ግሎ
    0.37
     концу
    0.37
     nowe
    0.36
     définir
    0.36
     visión
    0.36
    ifferentiated
    0.36
    POSITIVE LOGITS
     해당
    0.78
     उस
    0.66
     जिस
    0.65
     relevant
    0.64
    那個
    0.62
    relevant
    0.60
     applicable
    0.59
    当該
    0.57
    那个
    0.57
     соответству
    0.57
    Act Density 0.093%

    No Known Activations