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

    Neuronpedia

    INDEX
    Explanations

    references to technical specifications or components in descriptions

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

    Followed by technical terms, parentheses, or symbols

    np_acts-logits-general · gemini-2.0-flash

    concepts and their attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.85
    CppMethod
    -0.85
    Personendaten
    -0.81
    yntaxException
    -0.79
     Administrativna
    -0.79
     ProtoMessage
    -0.79
    InitVars
    -0.78
    AddTagHelper
    -0.77
    ThroughAttribute
    -0.77
     henvisninger
    -0.76
    POSITIVE LOGITS
     aka
    0.61
    WebServlet
    0.60
     approach
    0.59
     with
    0.57
    賀状
    0.53
     concept
    0.52
     scheme
    0.52
     (
    0.52
     scenario
    0.52
     (>
    0.51
    Act Density 1.987%

    No Known Activations