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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software updates and fixes

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

    fixed bugs and false alarms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.90
     ujednoznacz
    -0.89
     ſind
    -0.76
    Hentet
    -0.73
     transférez
    -0.73
    ChildScrollView
    -0.70
    tanleria
    -0.69
     ―――――
    -0.69
     مرئيه
    -0.68
    esgue
    -0.68
    POSITIVE LOGITS
    try
    0.42
    ↵↵
    0.40
     oldu
    0.37
     So
    0.37
    version
    0.37
     Yet
    0.37
     recently
    0.37
    1
    0.36
    2
    0.36
    ↵
    0.35
    Act Density 0.025%

    No Known Activations