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

    Neuronpedia

    INDEX
    Explanations

    instances of closure or ending concepts in various contexts

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

    associated with "closed" or "closing"

    np_acts-logits-general · gemini-2.0-flash

    behind closed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.58
    ContentAsync
    -0.51
    لينكات
    -0.51
    الدراسه
    -0.49
    NamedQueries
    -0.47
     sorteo
    -0.47
    phus
    -0.47
    setHas
    -0.46
    reibe
    -0.46
     kaynağından
    -0.46
    POSITIVE LOGITS
     closed
    3.58
     closing
    3.31
     closes
    3.21
     Closed
    3.17
     closure
    3.12
    closed
    3.06
     Closing
    2.97
    Closed
    2.93
     clos
    2.83
    Closing
    2.81
    Act Density 0.477%

    No Known Activations