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

    Neuronpedia

    INDEX
    Explanations

    bestow upon or extraordinary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    1.30
    </h3>
    1.28
    </h2>
    1.22
     wody
    1.20
     I
    1.19
    การ
    1.17
     capa
    1.13
     anodes
    1.12
     arada
    1.09
    </h4>
    1.07
    POSITIVE LOGITS
    ul
    1.52
    á
    1.50
    g
    1.49
    c
    1.30
    ü
    1.25
    ем
    1.22
    ви
    1.20
    il
    1.20
    ен
    1.17
    онов
    1.16
    Act Density 0.000%

    No Known Activations