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

    Neuronpedia

    INDEX
    Explanations

    references to time periods and changes over time

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

    recent timeframes

    np_acts-logits-general · gemini-2.0-flash

    duration of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.64
    Rohy
    -0.63
    AddTagHelper
    -0.62
     архивлан
    -0.61
     дописавши
    -0.61
     Signalez
    -0.60
    featureID
    -0.59
     Winaray
    -0.58
    IENTE
    -0.57
    InitVars
    -0.57
    POSITIVE LOGITS
     last
    2.66
     past
    2.45
    last
    2.07
    past
    1.92
    Last
    1.89
     afgelopen
    1.84
     Last
    1.80
     letzten
    1.77
     vergangenen
    1.77
     últimos
    1.67
    Act Density 0.205%

    No Known Activations