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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to court cases

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

    state court locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.40
    is
    -0.37
    ‌
    -0.37
    ance
    -0.36
    c
    -0.35
    ary
    -0.35
    ENOS
    -0.35
    to
    -0.35
    сто
    -0.34
     or
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.91
    parsedMessage
    0.85
     disambiguazione
    0.84
     erſt
    0.81
     Administrativna
    0.81
    [@BOS@]
    0.80
    <unused41>
    0.79
    <unused43>
    0.79
    <unused14>
    0.79
    <unused8>
    0.79
    Act Density 0.002%

    No Known Activations