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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to legal proceedings and evidence

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

    distinguishing differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bor
    -0.28
     and
    -0.27
     s
    -0.26
    -
    -0.26
    ↵↵
    -0.26
     .
    -0.25
     fazenda
    -0.25
    ).
    -0.25
     t
    -0.25
     
    -0.25
    POSITIVE LOGITS
     queſta
    0.89
    ագրություններ
    0.80
     Normdatei
    0.80
    SourceChecksum
    0.79
     BoxFit
    0.78
     surla
    0.75
    parsedMessage
    0.75
     queſto
    0.75
     Signalez
    0.74
     للاسماء
    0.73
    Act Density 0.395%

    No Known Activations