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

    Neuronpedia

    INDEX
    Explanations

    fantasy book titles and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retro
    0.48
     Retro
    0.48
    retro
    0.40
     AppException
    0.40
     Fairfax
    0.39
    妖怪
    0.38
    espèces
    0.38
    ጫ
    0.38
     Regional
    0.38
     регионе
    0.38
    POSITIVE LOGITS
     Ged
    0.56
    Brandon
    0.50
     sword
    0.47
     Brandon
    0.46
     swords
    0.44
     Robin
    0.43
     Prism
    0.43
    Robin
    0.42
     mage
    0.42
     memory
    0.41
    Act Density 0.011%

    No Known Activations