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

    Neuronpedia

    INDEX
    Explanations

    via connections and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.10
    на
    1.09
    ように
    1.01
     కోసం
    0.87
    е
    0.85
     народов
    0.84
     maaaring
    0.84
    nt
    0.83
    Seperti
    0.83
     assemble
    0.82
    POSITIVE LOGITS
     deren
    0.84
     capita
    0.82
    asarray
    0.82
    href
    0.81
    argin
    0.81
    跹
    0.80
     അതിന്റെ
    0.79
    padding
    0.78
    avond
    0.78
     evidenced
    0.77
    Act Density 0.509%

    No Known Activations