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

    Neuronpedia

    INDEX
    Explanations

    specific legal terms and accurate representations of legal standards

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

    "exact" or variants

    np_acts-logits-general · gemini-2.0-flash

    exactness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     通販
    -0.50
    endfor
    -0.49
    paravant
    -0.48
    σμο
    -0.47
     Савезне
    -0.47
     dahulu
    -0.46
     magasiner
    -0.46
    дравству
    -0.45
    Билгалдахарш
    -0.45
     verzichten
    -0.45
    POSITIVE LOGITS
     exact
    2.52
     exactly
    2.33
    exact
    2.21
     Exact
    2.13
    exactly
    2.13
     EXACTLY
    2.08
     EXACT
    2.06
     Exactly
    2.04
    Exact
    1.99
     precise
    1.98
    Act Density 0.448%

    No Known Activations