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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirming or verifying actions

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

    Slavic words, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.44
     الرياضيه
    -0.41
     crane
    -0.40
    Cubit
    -0.39
    WebServlet
    -0.38
     brancas
    -0.38
    ViewImports
    -0.37
     createState
    -0.37
     transit
    -0.36
    Mercedes
    -0.36
    POSITIVE LOGITS
    enumii
    0.72
    :✨
    0.63
    Pog
    0.54
    posedge
    0.51
     Post
    0.50
    qtype
    0.50
    rungsseite
    0.50
    enumi
    0.50
     по
    0.49
    onViewCreated
    0.49
    Act Density 0.006%

    No Known Activations