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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and quantities

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

    time relative to now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.47
    日起
    -0.39
    :✨
    -0.36
    terminator
    -0.36
    ÈME
    -0.36
    iello
    -0.35
    httphttps
    -0.35
    fford
    -0.34
    opter
    -0.33
    xter
    -0.33
    POSITIVE LOGITS
     ब्रेकडाउन
    0.54
    SEGUIR
    0.51
    aarrggbb
    0.50
    以上的
    0.48
    左右
    0.48
     CreateTagHelper
    0.46
    GEBURTSDATUM
    0.46
    bibfield
    0.46
    Autoritní
    0.46
     izquier
    0.45
    Act Density 0.008%

    No Known Activations