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

    Neuronpedia

    INDEX
    Explanations

    playing on narrative elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hadoop
    0.35
     RoHS
    0.33
     optimizes
    0.33
     ETL
    0.33
     optimizing
    0.31
     ReLU
    0.30
     kWh
    0.30
     aplik
    0.30
     applications
    0.30
     methodologies
    0.30
    POSITIVE LOGITS
     personagens
    0.62
     personnages
    0.62
     personajes
    0.59
     сюжет
    0.57
     personaje
    0.55
     personagem
    0.54
    剧情
    0.54
     characters
    0.54
    描写
    0.53
     backstory
    0.53
    Act Density 1.982%

    No Known Activations