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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their statements or contributions

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

    speaker attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.71
    LookAnd
    -0.66
    XmlAccessorType
    -0.66
    PerformLayout
    -0.59
    interopRequire
    -0.58
     مشين
    -0.58
    IUrlHelper
    -0.58
    ValueStyle
    -0.57
    Personensuche
    -0.55
    RegistryLite
    -0.54
    POSITIVE LOGITS
     points
    0.35
     Behör
    0.34
     Überg
    0.34
     panggilan
    0.34
     Änder
    0.34
     Räume
    0.34
     ruedas
    0.33
     point
    0.33
     Verpflichtung
    0.33
     puntos
    0.33
    Act Density 0.010%

    No Known Activations