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

    Neuronpedia

    INDEX
    Explanations

    sections or indicators of code comments and documentation

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

    Code comments and headers

    np_acts-logits-general · gemini-2.0-flash

    code comments and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.71
     spacy
    -0.55
    DOCTYPE
    -0.53
     ArrayAdapter
    -0.53
    gameserver
    -0.52
     typename
    -0.52
    ècie
    -0.52
    AsUp
    -0.52
    Ӧ
    -0.50
     tensorflow
    -0.50
    POSITIVE LOGITS
    Datuak
    0.76
     autorytatywna
    0.73
    RenderAtEndOf
    0.73
    Rohy
    0.65
    engelsk
    0.55
    mergeFrom
    0.51
    ArgumentParser
    0.49
    älfte
    0.49
    BeginContext
    0.48
     iArr
    0.47
    Act Density 0.346%

    No Known Activations