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

    Neuronpedia

    INDEX
    Explanations

    references to programming events and components in a software context

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

    CommandType or <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.66
     pleaſure
    -0.63
    DockStyle
    -0.63
     Anſ
    -0.62
     ſche
    -0.61
     utafitiHapana
    -0.59
     raiſ
    -0.58
     purpoſe
    -0.56
     habet
    -0.53
    gjenge
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    1.74
    ScopeManager
    1.50
     AssemblyCompany
    1.16
    بوابة
    1.04
     ويكيپيديا
    1.02
     BoxDecoration
    1.01
     Bourgoin
    0.85
    RequestMethod
    0.82
     consectetur
    0.81
    الإنجليزية
    0.75
    Act Density 0.001%

    No Known Activations