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

    Neuronpedia

    INDEX
    Explanations

    references to various kinds of items

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

    listing of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.73
    󠁮
    -0.57
     hydrostatic
    -0.55
     forState
    -0.53
    raulic
    -0.53
    expectations
    -0.50
     McLaughlin
    -0.50
     useAuth
    -0.50
     electrostatic
    -0.49
     Geophysics
    -0.49
    POSITIVE LOGITS
     items
    1.81
     Items
    1.56
     item
    1.50
    items
    1.44
    Items
    1.40
     ITEMS
    1.35
     Item
    1.24
    Item
    1.21
    ITEMS
    1.11
     ITEM
    1.09
    Act Density 0.018%

    No Known Activations