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

    Neuronpedia

    INDEX
    Explanations

    technical details about software updates and bug fixes

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

    Fixing software or hardware issues

    np_acts-logits-general · gemini-2.0-flash

    problems and fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.70
     فريبيس
    -0.61
     Вікіпе
    -0.60
    BeginContext
    -0.58
    -0.56
     صوتيه
    -0.56
    classnames
    -0.54
    ValueGeneration
    -0.54
     оригіналу
    -0.52
    AndEndTag
    -0.51
    POSITIVE LOGITS
     problems
    1.47
     bug
    1.44
     bugs
    1.34
     malfunctions
    1.30
     malfunction
    1.29
    problems
    1.27
     problem
    1.27
     glitch
    1.27
     glitches
    1.27
     Problems
    1.25
    Act Density 0.546%

    No Known Activations