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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate observation or perception

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

    seeing what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    powiedz
    -0.43
     âmes
    -0.43
     gevoel
    -0.42
     يتيمه
    -0.41
     linguistique
    -0.40
     betweenstory
    -0.40
     politiker
    -0.39
    hörige
    -0.39
     bertanggung
    -0.38
     religione
    -0.37
    POSITIVE LOGITS
     visible
    0.75
     evident
    0.60
     visibly
    0.60
     Visible
    0.56
     seen
    0.55
    idać
    0.54
    ViewChild
    0.53
     seeing
    0.53
     obvious
    0.53
     observable
    0.52
    Act Density 0.081%

    No Known Activations