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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" and its variants

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

    when initiating temporal clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.55
     IndexPath
    -0.47
    casila
    -0.47
     doInBackground
    -0.47
     Savo
    -0.45
    ])))
    -0.44
    _))
    -0.44
    sizeCache
    -0.44
     pyplot
    -0.43
    俯
    -0.43
    POSITIVE LOGITS
     When
    0.47
    0.43
     Když
    0.43
     Когда
    0.42
    When
    0.41
     Kiedy
    0.40
     Cuando
    0.39
     Quando
    0.38
     Lorsque
    0.38
     يتيمه
    0.37
    Act Density 0.030%

    No Known Activations