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

    Neuronpedia

    INDEX
    Explanations

    role-play fiction, fantasies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    руются
    0.47
    ються
    0.44
    ឯ
    0.44
     ਹੀ
    0.42
     ("",
    0.42
    დება
    0.40
     focuss
    0.40
    웜
    0.39
    ierre
    0.39
    зации
    0.38
    POSITIVE LOGITS
     get
    0.65
    Get
    0.50
    get
    0.49
     Get
    0.49
     gets
    0.48
     getContent
    0.48
    ][
    0.44
     afficher
    0.44
     finalize
    0.44
     getUser
    0.42
    Act Density 0.004%

    No Known Activations