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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, particularly referencing durations and past events

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

    "[Number] years ago/later"

    np_acts-logits-general · gemini-2.0-flash

    years ago or later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.76
     Inſ
    -0.71
     Diſ
    -0.69
     ſind
    -0.68
     Perſ
    -0.68
     Anſ
    -0.67
     Majefty
    -0.67
    ſelves
    -0.67
    DispatchToProps
    -0.65
     Monfieur
    -0.64
    POSITIVE LOGITS
     ago
    1.05
     geleden
    0.71
     years
    0.64
     hinweg
    0.62
     now
    0.60
     since
    0.60
     atrás
    0.59
     today
    0.57
     anni
    0.56
     anniversary
    0.56
    Act Density 0.112%

    No Known Activations