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

    Neuronpedia

    INDEX
    Explanations

    definitions and discussions around concepts, especially those that are subjective or open to interpretation

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

    definitions

    np_acts-logits-general · gemini-2.0-flash

    defining concepts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noted
    -0.42
    Gilla
    -0.42
    entious
    -0.41
    Noted
    -0.40
    Resumo
    -0.40
    LastError
    -0.40
    ToolStrip
    -0.40
    CreateModel
    -0.39
    >(_
    -0.38
    디어
    -0.38
    POSITIVE LOGITS
     definition
    1.19
     definitions
    1.04
     define
    1.00
     Definition
    0.96
     defines
    0.95
    所謂
    0.93
    definition
    0.91
     DEFINITION
    0.91
    什么是
    0.88
     définition
    0.88
    Act Density 0.310%

    No Known Activations