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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাড়া
    0.44
     ද
    0.43
    deel
    0.43
    သို့
    0.42
    enas
    0.42
     thisTrial
    0.42
    ල
    0.42
     Гру
    0.42
     Тому
    0.42
    ້ອ
    0.41
    POSITIVE LOGITS
     Exeter
    0.51
    CE
    0.48
    ER
    0.48
     hindsight
    0.46
     garb
    0.44
    נ
    0.44
     বিবি
    0.44
    IT
    0.43
     ateliers
    0.43
     collections
    0.43
    Act Density 0.010%

    No Known Activations