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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically in terms of months or month durations

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

    specific time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CommandType
    -0.40
    radical
    -0.39
     Miche
    -0.38
     élas
    -0.38
     Fray
    -0.38
    Bram
    -0.37
     niew
    -0.37
     transgression
    -0.37
     FileNotFound
    -0.36
     Bram
    -0.36
    POSITIVE LOGITS
    Semi
    0.62
     Half
    0.62
     half
    0.62
    Personendaten
    0.61
     चीज़ों
    0.60
     Semi
    0.60
    half
    0.60
     HALF
    0.59
     halve
    0.58
    Half
    0.58
    Act Density 0.097%

    No Known Activations