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

    Neuronpedia

    INDEX
    Explanations

    if necessary or applicable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    했고
    0.68
     proverbial
    0.67
     혹
    0.67
     moguć
    0.66
    िटर
    0.63
     probablemente
    0.63
    었고
    0.63
     няма
    0.61
     isoform
    0.61
     možnost
    0.61
    POSITIVE LOGITS
     உங்கள்
    0.67
    orbits
    0.63
     your
    0.61
     youll
    0.61
     você
    0.60
    DataMat
    0.60
    corr
    0.59
    MQ
    0.59
     slik
    0.59
     आपके
    0.59
    Act Density 0.003%

    No Known Activations