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

    Neuronpedia

    INDEX
    Explanations

    legal terms and references to court procedures

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

    Numbers within court documents

    np_acts-logits-general · gemini-2.0-flash

    numbers and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    linawan
    -1.04
    AddTagHelper
    -1.00
    <unused74>
    -0.98
    <unused41>
    -0.98
    ロウィン
    -0.98
    <unused28>
    -0.97
    <unused43>
    -0.97
    <unused14>
    -0.97
    <pad>
    -0.97
    <unused8>
    -0.97
    POSITIVE LOGITS
    ↵↵↵
    1.21
    ↵↵↵↵↵
    0.94
    ↵↵↵↵
    0.93
    ↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵
    0.79
    ↵↵↵↵↵↵↵↵↵
    0.71
    ↵↵↵↵↵↵↵↵
    0.70
    ↵↵↵↵↵↵↵↵↵↵↵
    0.63
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.60
    ↵↵↵↵↵↵↵↵↵↵
    0.60
    Act Density 0.075%

    No Known Activations