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

    Neuronpedia

    INDEX
    Explanations

    terms related to risk assessment

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

    at risk of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ▬▬▬▬▬▬▬▬
    -0.41
     calcetines
    -0.40
     плю
    -0.38
     păr
    -0.37
     lisäksi
    -0.37
     demonios
    -0.37
     tuttavia
    -0.36
     הוד
    -0.35
     rempliss
    -0.35
     صفحۀ
    -0.35
    POSITIVE LOGITS
     jeopardy
    0.65
    bufio
    0.58
    opardy
    0.57
     vulnerable
    0.56
     endangered
    0.56
     susceptible
    0.55
     zagro
    0.54
     threatened
    0.52
    reportWebVitals
    0.52
    ronpa
    0.51
    Act Density 0.006%

    No Known Activations