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

    Neuronpedia

    INDEX
    Explanations

    references to envelopes and containers in the text

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

    containers for items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.53
     المعيارى
    -0.52
    taminophen
    -0.51
    fantasia
    -0.50
     gynhyrchwyd
    -0.49
     kasarigan
    -0.48
    insics
    -0.47
    InitVars
    -0.46
     SwitchCompat
    -0.45
    pography
    -0.45
    POSITIVE LOGITS
     bag
    0.66
     jar
    0.65
     jars
    0.60
     bags
    0.54
     basket
    0.54
    Bag
    0.51
    Bags
    0.51
     envelope
    0.50
     Bag
    0.50
     box
    0.49
    Act Density 0.064%

    No Known Activations