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

    Neuronpedia

    INDEX
    Explanations

    references to arch-related terms or titles

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

    arch, archduke, archbishop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    -0.40
    fü
    -0.34
    ening
    -0.32
    便
    -0.32
    ener
    -0.32
    e
    -0.32
    Terry
    -0.32
    🏼
    -0.32
    NON
    -0.30
     Нет
    -0.30
    POSITIVE LOGITS
     Arch
    0.78
    Nuorodos
    0.72
     arch
    0.66
     Arches
    0.65
    expandindo
    0.65
    ibald
    0.63
     ARCH
    0.62
    ikusbot
    0.60
    Cyfeiriadau
    0.60
    Arch
    0.59
    Act Density 0.009%

    No Known Activations