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

    Neuronpedia

    INDEX
    Explanations

    patterns of text structure or formatting, particularly related to sequences or lists

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

    solve mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.69
     mergeFrom
    -0.52
    ftagPool
    -0.52
    MLLoader
    -0.52
    featureID
    -0.49
     nahilalakip
    -0.48
    Hozzáférés
    -0.46
    Personendaten
    -0.46
    verifyException
    -0.46
    WithIOException
    -0.46
    POSITIVE LOGITS
    琴
    0.51
     опу
    0.47
    Quite
    0.45
    Gar
    0.45
    pog
    0.45
    Auto
    0.45
    Destination
    0.44
    huma
    0.43
    Trinity
    0.43
    Fine
    0.43
    Act Density 0.004%

    No Known Activations