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

    Neuronpedia

    INDEX
    Explanations

    references to help, tutorials, and instructional content

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

    help and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.52
    SerializeField
    -0.51
     jullie
    -0.47
     zoude
    -0.47
     energética
    -0.45
     būs
    -0.45
    期刊论文
    -0.43
    ⇋
    -0.42
    IsMutable
    -0.42
    RectangleBorder
    -0.41
    POSITIVE LOGITS
     Guides
    0.58
     guides
    0.54
     instruction
    0.49
     explanations
    0.48
     tute
    0.47
    Guides
    0.46
     Training
    0.46
     instru
    0.45
     guide
    0.45
     hints
    0.45
    Act Density 0.024%

    No Known Activations