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

    Neuronpedia

    INDEX
    Explanations

    references to "Harry Potter" or related terms

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

    Potter, Rowling, pottery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combineReducers
    -0.59
    BagConstraints
    -0.54
     Lightboxes
    -0.49
     invokingState
    -0.49
    sizeCache
    -0.49
    iosync
    -0.49
    databind
    -0.48
     Signal
    -0.47
    posedge
    -0.47
     signal
    -0.47
    POSITIVE LOGITS
     Potter
    2.42
    Potter
    2.14
     potter
    1.57
     POT
    0.69
     Pottery
    0.66
     Harry
    0.65
    pot
    0.64
     Pott
    0.63
    Potion
    0.63
    Harry
    0.61
    Act Density 0.002%

    No Known Activations