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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating oversight, observation, or significant spatial positioning

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

    over and overlooking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Trace
    -0.42
     Trace
    -0.40
    rån
    -0.34
     quitar
    -0.34
    trace
    -0.31
     trace
    -0.30
     anecd
    -0.30
     correctes
    -0.29
     palo
    -0.28
     идей
    -0.28
    POSITIVE LOGITS
     overview
    0.61
    overview
    0.59
    IBOutlet
    0.58
     CreateTagHelper
    0.57
     overseeing
    0.57
     asupra
    0.56
     مرئيه
    0.56
     laſſen
    0.54
    retudo
    0.53
    俯
    0.53
    Act Density 0.028%

    No Known Activations