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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes or terms related to disappointment or unfavorable conditions

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

    starting with "Un" prefix

    np_acts-logits-general · gemini-2.0-flash

    words starting with "un"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ADVERTISEMENT
    -0.70
     GenerationType
    -0.65
    enumi
    -0.64
     وتسجيلات
    -0.64
     MainAxisSize
    -0.61
     createState
    -0.59
    Takeaway
    -0.59
     BoxDecoration
    -0.57
     tantôt
    -0.56
    richTextPanel
    -0.56
    POSITIVE LOGITS
     un
    1.00
     UN
    0.98
     Un
    0.96
    Un
    0.84
    un
    0.74
    UN
    0.74
     unf
    0.74
     unt
    0.73
     تضيفلها
    0.70
     unw
    0.67
    Act Density 0.115%

    No Known Activations