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

    Neuronpedia

    INDEX
    Explanations

    commands or requests directed towards the user

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

    modal verbs and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iseite
    -0.45
     Brice
    -0.44
    TestMethod
    -0.44
    msgTypes
    -0.43
    itated
    -0.42
    OrderStatus
    -0.42
    EndInit
    -0.41
     Selama
    -0.41
    rinfo
    -0.41
    umed
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.60
     GenerationType
    0.47
    rrggbb
    0.39
    seers
    0.36
    المناصب
    0.35
    Aiheesta
    0.35
     تكبرها
    0.34
     disambiguazione
    0.34
    ыгана
    0.33
     themselves
    0.33
    Act Density 0.112%

    No Known Activations