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

    Neuronpedia

    INDEX
    Explanations

    legal references and citations in court documents

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

    legal section citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pecabe
    -0.90
    iſchen
    -0.86
    ロウィン
    -0.86
    AddTagHelper
    -0.84
    ﹧
    -0.83
    iſten
    -0.83
    <unused41>
    -0.82
    <unused16>
    -0.81
    <unused14>
    -0.81
    <unused8>
    -0.81
    POSITIVE LOGITS
     linkovi
    0.29
    audiovisuel
    0.29
     Roskov
    0.29
    に
    0.29
    TSCA
    0.28
     podjela
    0.27
    чность
    0.26
     as
    0.26
    k
    0.26
     wo
    0.26
    Act Density 0.110%

    No Known Activations