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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the formation and actions of groups or organizations

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

    works with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.62
     resourceCulture
    -0.62
     linkovi
    -0.55
    ंदीखरीदारी
    -0.52
     surla
    -0.51
    épa
    -0.50
     الرياضيه
    -0.48
    lectricité
    -0.48
    rrggbb
    -0.48
     createState
    -0.48
    POSITIVE LOGITS
     "
    0.38
     “
    0.38
    TokenNameRBRACE
    0.35
    ModelState
    0.35
    %%%%%%%%%%%%%%%%
    0.35
    冈
    0.35
     „
    0.35
    ：「
    0.35
     "<?
    0.34
    setLong
    0.34
    Act Density 0.067%

    No Known Activations