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

    Neuronpedia

    INDEX
    Explanations

    roleplay characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    risk
    0.56
    revenue
    0.56
     efficiencies
    0.55
    quantile
    0.54
    analysis
    0.52
     SOLUTIONS
    0.50
    reliant
    0.49
    allclasses
    0.48
     reforms
    0.48
    research
    0.48
    POSITIVE LOGITS
     personaje
    0.93
     personnage
    0.85
     personaggio
    0.82
     personagem
    0.81
    剧情
    0.80
     fantasy
    0.78
    场景
    0.78
     anime
    0.77
     Anime
    0.77
     chibi
    0.77
    Act Density 0.685%

    No Known Activations