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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships between multiple elements or components

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liceerd
    -0.45
    IMDG
    -0.42
     Wicidata
    -0.40
     rendono
    -0.37
    Lur
    -0.37
     distinction
    -0.36
    ภัย
    -0.35
    Personendaten
    -0.35
    ivez
    -0.35
    CastException
    -0.35
    POSITIVE LOGITS
     beginnetje
    0.50
    ніципалі
    0.47
     birbir
    0.47
    SpringBootTest
    0.45
    ynnwys
    0.42
    interopRequire
    0.42
     мәкалә
    0.40
     pinulongan
    0.40
    chartInstance
    0.40
    jamientos
    0.39
    Act Density 0.237%

    No Known Activations