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

    Neuronpedia

    INDEX
    Explanations

    prepositions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meski
    0.36
     பணிகள்
    0.36
     económ
    0.34
     schützen
    0.34
     schnelle
    0.34
     sueños
    0.33
     clés
    0.33
     মতোই
    0.33
     dérivés
    0.33
     fórm
    0.33
    POSITIVE LOGITS
    以下の
    0.37
    의
    0.36
    ул
    0.36
    До
    0.34
    టువంటి
    0.33
    라는
    0.33
     नामक
    0.33
    ᡠ
    0.33
    а
    0.33
    ро
    0.32
    Act Density 0.259%

    No Known Activations