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

    Neuronpedia

    INDEX
    Explanations

    references to the concept and manipulation of time

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

    time followed by actions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.57
    ThroughAttribute
    -0.52
    MLLoader
    -0.48
    +#+
    -0.48
    참고
    -0.48
    endum
    -0.47
    Примітки
    -0.46
     mergeFrom
    -0.46
     surla
    -0.45
    dro
    -0.45
    POSITIVE LOGITS
     time
    0.83
     Time
    0.80
     TIME
    0.76
    Time
    0.70
    ⏳
    0.67
    时间
    0.64
     tiempo
    0.63
     시간
    0.61
    ⌛
    0.60
     时间
    0.60
    Act Density 0.036%

    No Known Activations