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

    Neuronpedia

    INDEX
    Explanations

    terms related to architectural elements and features, specifically arches

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

    arch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Niet
    -0.45
    })}\
    -0.45
    件
    -0.42
    })$}
    -0.42
     Faso
    -0.41
     nore
    -0.41
    )}}{
    -0.41
    ]!=
    -0.40
     Mino
    -0.40
    WEBPACK
    -0.40
    POSITIVE LOGITS
     arch
    1.66
     arches
    1.59
     arched
    1.31
     Arches
    1.25
    arching
    0.93
     ARCH
    0.88
    拱
    0.87
    arch
    0.85
     arcos
    0.85
     Arch
    0.84
    Act Density 0.002%

    No Known Activations