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

    Neuronpedia

    INDEX
    Explanations

    references to legal documents and the processes associated with them

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

    document verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.57
    IntoConstraints
    -0.56
    Personensuche
    -0.54
    BeginContext
    -0.51
    Gön
    -0.51
    TagMode
    -0.48
     CreateTagHelper
    -0.47
    Ranks
    -0.46
     StatefulWidget
    -0.45
    Rptr
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.39
     decât
    0.33
     Gerald
    0.31
     közül
    0.31
    Identyfik
    0.30
     pessoais
    0.30
     conces
    0.29
     MQ
    0.29
     atriz
    0.29
    CEPTION
    0.29
    Act Density 0.107%

    No Known Activations