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

    Neuronpedia

    INDEX
    Explanations

    Harry Potter universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bridgeport
    0.83
     গার্ম
    0.83
     TEX
    0.78
     urban
    0.76
     도시
    0.73
     CDK
    0.72
    渚
    0.71
    滨
    0.71
     trucker
    0.71
     కార్
    0.71
    POSITIVE LOGITS
     Hogwarts
    2.30
     Harry
    2.17
    Harry
    2.07
     wizards
    1.97
     wizard
    1.82
     Potter
    1.81
    harry
    1.78
     Wizard
    1.77
     Rowling
    1.75
     Vold
    1.74
    Act Density 0.063%

    No Known Activations