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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming frameworks and test functionalities

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

    user turn marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vastaan
    -0.49
    XMLSchema
    -0.45
    Referências
    -0.44
    েকে
    -0.43
     afhankelijk
    -0.41
    ksesta
    -0.41
    ļu
    -0.41
    ethical
    -0.40
    undes
    -0.39
    verley
    -0.39
    POSITIVE LOGITS
    appBar
    1.27
    IsMutable
    0.68
    sidemargin
    0.68
    richTextPanel
    0.66
    AnchorStyles
    0.62
    DockStyle
    0.61
    windowFixed
    0.59
    gtest
    0.59
    flashdata
    0.59
    BufferException
    0.59
    Act Density 0.000%

    No Known Activations