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

    Neuronpedia

    INDEX
    Explanations

    aspects of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possíveis
    0.44
     estas
    0.41
     estes
    0.37
     พร้อม
    0.37
    此类
    0.36
    estes
    0.36
     คู่
    0.36
     semelhantes
    0.36
    Easy
    0.36
     möjligt
    0.36
    POSITIVE LOGITS
     aspect
    1.32
     idea
    1.17
     aspekt
    1.00
     argument
    0.99
     पहलू
    0.99
     issue
    0.98
     thing
    0.97
     Aspect
    0.96
     aspecto
    0.96
     hypothesis
    0.94
    Act Density 0.061%

    No Known Activations