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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and locations in the Harry Potter series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Harry Potter book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sorella
    -0.35
     fratello
    -0.32
     sostanza
    -0.31
     pendientes
    -0.30
     dip
    -0.29
     meubles
    -0.28
     móveis
    -0.28
    geblich
    -0.28
    见状
    -0.28
    getragen
    -0.28
    POSITIVE LOGITS
    0.68
    Personendaten
    0.67
    CloseOperation
    0.65
    RegressionTest
    0.65
    SequentialGroup
    0.58
    ParallelGroup
    0.58
    aarrggbb
    0.57
    PickerController
    0.54
    tinyos
    0.54
     bezeichneter
    0.53
    Act Density 0.032%

    No Known Activations