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

    Neuronpedia

    INDEX
    Explanations

    time-related terms, especially those indicating long durations

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

    years of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เอง
    -0.47
     trouvez
    -0.45
     serez
    -0.44
     aviones
    -0.43
     escaleras
    -0.43
    ,
    -0.43
     césped
    -0.43
     trenes
    -0.43
     papeles
    -0.43
     aurez
    -0.42
    POSITIVE LOGITS
    OGND
    0.94
    __":
    0.79
    Portail
    0.79
    fjspx
    0.77
     للاسماء
    0.73
    ValueStyle
    0.71
    __':
    0.70
    DockStyle
    0.70
     الاطلاع
    0.69
    الحياه
    0.67
    Act Density 0.015%

    No Known Activations