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

    Neuronpedia

    INDEX
    Explanations

    the presence of section headers or formatting indicators commonly found in technical documents

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

    Click here for additional data file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.48
    Lugares
    -0.46
     protoimpl
    -0.45
    ToAction
    -0.44
    Sucesor
    -0.44
    +#+
    -0.42
     operazioni
    -0.40
     Lokales
    -0.40
    EndContext
    -0.39
    TagMode
    -0.39
    POSITIVE LOGITS
    BibitemShut
    0.60
    findpost
    0.52
    bibfield
    0.51
     nahilalakip
    0.49
    bibinfo
    0.48
     IDisposable
    0.46
    FlatStyle
    0.45
    timme
    0.45
     hangover
    0.44
     captioned
    0.44
    Act Density 0.001%

    No Known Activations