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

    Neuronpedia

    INDEX
    Explanations

    add and maintain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ইংরে
    0.45
    english
    0.44
     Bhub
    0.42
     english
    0.41
     ENGLISH
    0.40
     अने
    0.39
     respons
    0.39
     англий
    0.38
    ENGLISH
    0.38
    枷
    0.37
    POSITIVE LOGITS
    葷
    0.41
    維持
    0.39
     дов
    0.37
     Crust
    0.37
    <unused98>
    0.37
    Sun
    0.36
    Meat
    0.36
    姩
    0.36
    Grass
    0.36
     présenté
    0.36
    Act Density 0.003%

    No Known Activations