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

    Neuronpedia

    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ιδ
    0.44
    ｡
    0.42
     दिक्
    0.41
     એ
    0.41
    Personality
    0.41
     bienvenida
    0.38
    ᱞ
    0.38
     আলো
    0.38
     adding
    0.37
     reservados
    0.37
    POSITIVE LOGITS
     ஆண்டுகள்
    0.45
     ਅਤੇ
    0.45
    <unused636>
    0.44
    岁月
    0.44
    और
    0.41
    ティーク
    0.41
    䚰
    0.41
     истори
    0.41
    camore
    0.41
    <unused11>
    0.40
    Act Density 0.011%

    No Known Activations