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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, recommendations, or sequences involving "addition" and "well" in contexts suggesting improvement or enhancement

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

    "as well as"

    np_acts-logits-general · gemini-2.0-flash

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEX
    -0.82
    はじめに
    -0.71
    mybatisplus
    -0.70
    Rüyada
    -0.64
     CreateTagHelper
    -0.63
     MonoBehaviour
    -0.62
    HideFlags
    -0.61
     AssemblyTitle
    -0.59
    contentLoaded
    -0.58
    SharedDtor
    -0.57
    POSITIVE LOGITS
    nd
    1.04
     nd
    0.84
    বং
    0.71
    ND
    0.70
    Nd
    0.67
    md
    0.64
    amint
    0.62
     d
    0.59
    lld
    0.59
     Nd
    0.58
    Act Density 0.153%

    No Known Activations