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

    Neuronpedia

    INDEX
    Explanations

    closing braces in code snippets

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

    foreign words and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.57
    grine
    -0.48
     noDo
    -0.46
    TryDecodeAsNil
    -0.44
    ViewInit
    -0.44
     Exactos
    -0.43
    DockStyle
    -0.43
    XmlAccessorType
    -0.42
     Taktlose
    -0.40
    FormTagHelper
    -0.40
    POSITIVE LOGITS
    verwijspagina
    0.53
     rzecz
    0.51
     כן
    0.43
     Audiodateien
    0.43
    ↵↵
    0.43
     préfé
    0.42
    ChildScrollView
    0.41
     pubblici
    0.41
    ientôt
    0.40
     refirió
    0.39
    Act Density 0.001%

    No Known Activations