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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols in the text

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

    convergence probability to zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.65
    fromnode
    -0.50
    engagent
    -0.49
     tantôt
    -0.48
     queſta
    -0.47
     Exactos
    -0.46
     tolerancia
    -0.46
    CGRectMake
    -0.46
     entornos
    -0.45
    StoryboardSegue
    -0.45
    POSITIVE LOGITS
    ChildScrollView
    0.62
    /******/
    0.51
    MathML
    0.50
    underbrace
    0.46
    addFlags
    0.44
    autoreleasepool
    0.43
    interopRequire
    0.43
    <thead>
    0.42
    estad
    0.42
    WidgetItem
    0.40
    Act Density 0.227%

    No Known Activations