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

    Neuronpedia

    INDEX
    Explanations

    sections that introduce or summarize academic papers and their contents

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

    document metadata and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meditación
    -0.46
     incendie
    -0.40
     escribiendo
    -0.39
     agresión
    -0.39
     discriminación
    -0.38
     exportaciones
    -0.38
     chrétien
    -0.37
     finanzas
    -0.37
     stabilization
    -0.37
     chrétiens
    -0.37
    POSITIVE LOGITS
    maketitle
    1.76
    setVerticalGroup
    0.78
    Personendaten
    0.74
    CppMethod
    0.73
     ProtoMessage
    0.69
     <<<<<<<<<<<<<<
    0.68
     ModelExpression
    0.66
     CreateTagHelper
    0.64
    хьтан
    0.62
    .*")]
    0.61
    Act Density 0.002%

    No Known Activations