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

    Neuronpedia

    INDEX
    Explanations

    programming-related language constructs and keywords

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

    code and special characters like CJK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.94
    TagMode
    -0.81
    richTextPanel
    -0.80
    IntoConstraints
    -0.78
     ſind
    -0.77
    ロウィン
    -0.76
     royaltyfri
    -0.75
    󠀠
    -0.75
     ProtoMessage
    -0.74
    RegressionTest
    -0.74
    POSITIVE LOGITS
    CJK
    0.36
    พาะ
    0.35
    ">(</
    0.34
    ̣t
    0.31
    >(</
    0.30
    displayquote
    0.28
    auml
    0.28
    |()
    0.28
    uuml
    0.28
    なく
    0.26
    Act Density 0.094%

    No Known Activations