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

    Neuronpedia

    INDEX
    Explanations

    questions or requests for assistance with programming and related topics

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

    "I am" or "I'm" at the beginning of a question/statement

    np_acts-logits-general · gemini-2.0-flash

    sentence end followed by I or But

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    прочем
    -0.74
     Efq
    -0.64
    =$?
    -0.64
     للمعارف
    -0.64
     وتسجيلات
    -0.62
     Савезне
    -0.62
    didSet
    -0.62
     persino
    -0.62
    AddTagHelper
    -0.61
     obstante
    -0.61
    POSITIVE LOGITS
     recently
    0.85
     Recently
    0.79
    recently
    0.76
    Recently
    0.76
     lately
    0.70
     Lately
    0.68
     currently
    0.65
     Currently
    0.65
    currently
    0.63
    Currently
    0.60
    Act Density 0.542%

    No Known Activations