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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax elements and structures

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

    two reviewers extracted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.52
    -0.52
    ęku
    -0.50
     Könige
    -0.50
    wußt
    -0.49
    backer
    -0.48
    ValueStyle
    -0.48
    ContentAsync
    -0.48
    Kjelder
    -0.48
    demás
    -0.47
    POSITIVE LOGITS
    ейс
    0.37
    Enumer
    0.37
     الس
    0.36
    縄
    0.36
     dam
    0.35
     judgment
    0.35
     Reſ
    0.35
    DYNAMIC
    0.33
    DataContract
    0.33
    μό
    0.33
    Act Density 0.001%

    No Known Activations