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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate balance or duality between different states or conditions

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

    while maintaining states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uved
    -0.39
     onPostExecute
    -0.35
     enví
    -0.29
     Archivado
    -0.29
     CHOICE
    -0.28
     läh
    -0.27
    rxjs
    -0.27
     enfermed
    -0.26
     concluyó
    -0.26
    ervlak
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.74
    OGND
    0.73
    XmlAccessType
    0.66
    MethodManager
    0.63
    IntoConstraints
    0.59
     AssemblyCulture
    0.59
    NameInMap
    0.59
     يتيمه
    0.58
    Personensuche
    0.58
    +#+#
    0.57
    Act Density 0.172%

    No Known Activations