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

    Neuronpedia

    INDEX
    Explanations

    terms related to entitlements and challenges in structured contexts

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

    policy or rule concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginInit
    -0.62
     BrowserModule
    -0.52
     useAppContext
    -0.48
     líquida
    -0.43
    MemoryWarning
    -0.43
    woordig
    -0.41
     avancée
    -0.41
     contemporaine
    -0.41
     intermédiaire
    -0.40
     contemporánea
    -0.40
    POSITIVE LOGITS
    iffance
    0.55
     Anſ
    0.55
    ciple
    0.54
     ſche
    0.53
     pleaſure
    0.52
    cipl
    0.50
     fester
    0.50
    ագրություններ
    0.49
    ſelf
    0.49
    nette
    0.49
    Act Density 0.050%

    No Known Activations