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

    Neuronpedia

    INDEX
    Explanations

    references to gratitude and acknowledgment in interactions

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

    aviation, locations, severity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.69
     الحره
    -0.60
    oa̍t
    -0.60
     AssemblyTitle
    -0.60
     invokingState
    -0.57
     صوتيه
    -0.57
    олові
    -0.57
     estekak
    -0.56
     مشين
    -0.56
     Geſch
    -0.55
    POSITIVE LOGITS
     prom
    0.41
    WebServlet
    0.37
     Ludwig
    0.35
     nommé
    0.33
    zyw
    0.32
    sockfd
    0.31
    ningss
    0.30
    Память
    0.29
     sendero
    0.29
    ytick
    0.29
    Act Density 0.091%

    No Known Activations