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

    Neuronpedia

    INDEX
    Explanations

    terms associated with restraint and confinement

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

    chain, locks, handcuffs, shackled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.87
    AndEndTag
    -0.86
     surla
    -0.73
     الرياضيه
    -0.73
     initComponents
    -0.71
    parsedMessage
    -0.66
     BytesLike
    -0.64
    transQ
    -0.62
     メンテナ
    -0.62
     ModelExpression
    -0.62
    POSITIVE LOGITS
     chain
    0.67
     chains
    0.61
     chained
    0.60
     Chain
    0.57
     padlock
    0.53
    Chain
    0.50
    chain
    0.47
     chaining
    0.47
     Chains
    0.46
     CHAIN
    0.46
    Act Density 0.025%

    No Known Activations