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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and their consequences

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

    causes and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uLocal
    -0.40
    Marcel
    -0.38
    Gente
    -0.37
    liceerd
    -0.37
    Grand
    -0.36
    lunda
    -0.35
     tila
    -0.35
    Phaser
    -0.35
    screen
    -0.34
    grand
    -0.34
    POSITIVE LOGITS
    StoreMessageInfo
    0.59
     unknownFields
    0.57
    点此举报
    0.52
    UnusedPrivate
    0.52
    MigrationBuilder
    0.51
    InputBorder
    0.51
    PerformLayout
    0.50
     désolés
    0.48
     Италијани
    0.48
    StructEnd
    0.46
    Act Density 0.401%

    No Known Activations