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

    Neuronpedia

    INDEX
    Explanations

    patterns in structured data or code formatting

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

    code blocks and academic text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.69
    RectangleBorder
    -0.62
    IContainer
    -0.61
    存于互联网档案馆
    -0.60
    DockStyle
    -0.60
    CppMethod
    -0.57
    Ruj
    -0.54
    AndroidJUnit
    -0.54
     مشين
    -0.54
     Sni
    -0.53
    POSITIVE LOGITS
     naciones
    0.54
     mandatario
    0.51
     zwey
    0.51
     stanga
    0.49
    adaptiveStyles
    0.49
     împre
    0.49
     ilmo
    0.49
    arangay
    0.47
     pagină
    0.47
    iegler
    0.47
    Act Density 0.069%

    No Known Activations