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

    Neuronpedia

    INDEX
    Explanations

    specific legal case references and citations

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

    decimal points and list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.65
     ,
    -0.49
    ",
    -0.37
    .
    -0.36
    <eos>
    -0.35
    ',
    -0.35
    (),
    -0.34
     $
    -0.33
    ),
    -0.33
    ++,
    -0.32
    POSITIVE LOGITS
     queſta
    0.75
     שוליים
    0.73
    BagLayout
    0.71
    RegistryLite
    0.67
     Houſe
    0.65
     leſs
    0.65
     ſeveral
    0.64
     ſind
    0.64
     ſta
    0.64
    ſelves
    0.63
    Act Density 0.654%

    No Known Activations