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

    Neuronpedia

    INDEX
    Explanations

    references to aides or assistance roles

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

    aide or helper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.77
    NoSuchAlgorithm
    -0.56
     MonoBehaviour
    -0.54
    QtWidgets
    -0.54
     Swann
    -0.53
    tidaknya
    -0.52
    unhofer
    -0.52
    convite
    -0.52
     aquarela
    -0.52
     doInBackground
    -0.51
    POSITIVE LOGITS
     aide
    1.95
     Aide
    1.74
     aides
    1.65
    Aide
    1.51
    aide
    1.23
     aider
    0.74
     aident
    0.72
    aider
    0.70
     ayude
    0.69
     helper
    0.68
    Act Density 0.003%

    No Known Activations