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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods and resources for improvement or guidance

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

    best guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.62
    Jeografia
    -0.52
     يتيمه
    -0.52
    anskje
    -0.51
     Италијани
    -0.50
     précédent
    -0.47
    webElementXpaths
    -0.46
    EndGlobalSection
    -0.45
    gameserver
    -0.45
     typelib
    -0.44
    POSITIVE LOGITS
     ſche
    0.43
     garanti
    0.42
     fool
    0.42
     guide
    0.41
     cram
    0.39
     חיצוניים
    0.39
     برانيه
    0.39
    azol
    0.38
    Guide
    0.38
    これで
    0.38
    Act Density 0.026%

    No Known Activations