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

    Neuronpedia

    INDEX
    Explanations

    numerical or list items and their relationships in a document

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

    programming and localization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.59
    AddTagHelper
    -0.57
     zwiſchen
    -0.55
     utafitiHapana
    -0.54
    ">//
    -0.53
    StoryboardSegue
    -0.52
     imagui
    -0.52
    CloseOperation
    -0.51
     HasFactory
    -0.50
    awaiter
    -0.50
    POSITIVE LOGITS
     citada
    0.54
     vôtre
    0.51
     libremente
    0.51
     citado
    0.50
     illustrationer
    0.49
     perdón
    0.49
     déta
    0.48
     nôtre
    0.48
     Formación
    0.48
     nødven
    0.47
    Act Density 0.001%

    No Known Activations