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

    Neuronpedia

    INDEX
    Explanations

    notable figures and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interesting
    0.85
     interessante
    0.79
    на
    0.67
     intéressante
    0.66
     utile
    0.65
     intéressant
    0.63
     amazing
    0.62
    interesting
    0.62
     interesante
    0.61
     Interesting
    0.61
    POSITIVE LOGITS
    ्स
    0.83
     زمانہ
    0.78
    DOUBLE
    0.63
     Defts
    0.62
     также
    0.62
     Barcelone
    0.59
     erster
    0.58
     Bourd
    0.57
    WASHINGTON
    0.57
    讳
    0.57
    Act Density 0.002%

    No Known Activations