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

    Neuronpedia

    INDEX
    Explanations

    content related to technology and software development issues

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

    Followed by "and"

    np_acts-logits-general · gemini-2.0-flash

    listing alongside and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maupun
    -0.86
    や
    -0.77
     lẫn
    -0.77
    ・
    -0.71
    -/
    -0.68
    -,
    -0.67
    /
    -0.66
     či
    -0.65
     والج
    -0.60
    やお
    -0.59
    POSITIVE LOGITS
     והוא
    1.60
    이고
    1.09
    并且
    1.05
     iar
    0.98
     ويمكن
    0.97
    并将
    0.95
     并
    0.95
     แล้ว
    0.94
     ولم
    0.90
    ConstraintMaker
    0.89
    Act Density 2.210%

    No Known Activations