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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that generally describe processes, specifications, systems, or methods.

    oai_token-act-pair · gemini-2.0-flash

    system

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalTable
    -0.64
    🏾
    -0.59
    :]:
    -0.55
     onResponse
    -0.54
     Sequelize
    -0.54
    сім
    -0.52
    migrationBuilder
    -0.51
    Portale
    -0.51
    )]{
    -0.51
    PreExecute
    -0.51
    POSITIVE LOGITS
    الإنجليزية
    0.81
    vician
    0.54
    évaluateur
    0.54
    zną
    0.54
     pö
    0.52
    msgTypes
    0.51
    acchi
    0.50
    دانشنامهٔ
    0.50
    afficheront
    0.49
     spread
    0.47
    Act Density 18.848%

    No Known Activations