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

    Neuronpedia

    INDEX
    Explanations

    mentions of company-related terms, particularly possessive references to teams or services

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

    organization's assets and objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.94
     ब्रेकडाउन
    -0.82
    AndEndTag
    -0.76
     nakalista
    -0.75
    verwijspagina
    -0.74
    utilisons
    -0.74
     autorytatywna
    -0.70
     snippetHide
    -0.67
    RegressionTest
    -0.66
    UrlResolution
    -0.64
    POSITIVE LOGITS
     commitment
    0.44
     team
    0.41
     mission
    0.40
     carefully
    0.40
     experts
    0.39
     aim
    0.39
     extensive
    0.38
     focus
    0.37
     partners
    0.35
     goal
    0.34
    Act Density 0.015%

    No Known Activations