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

    Neuronpedia

    INDEX
    Explanations

    key terms related to preservation and significance in various contexts

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

    preserve from, candidate as, appeared in, demonstrate that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.61
    +#+#
    -0.55
     scar
    -0.50
     cow
    -0.49
     stones
    -0.48
    RCA
    -0.47
     icing
    -0.47
    webElementXpaths
    -0.46
     aw
    -0.46
     saying
    -0.46
    POSITIVE LOGITS
     localObject
    0.59
    WriteBarrier
    0.52
    principalColumn
    0.51
    kijken
    0.50
    aarrggbb
    0.50
    Rüyada
    0.49
    httphttps
    0.48
    IUrlHelper
    0.48
    middels
    0.48
     eenig
    0.47
    Act Density 0.115%

    No Known Activations