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

    Neuronpedia

    INDEX
    Explanations

    temporal references related to duration

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

    years and duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     targeting
    -0.42
    ImageIO
    -0.40
     tricky
    -0.40
     betweenstory
    -0.40
     πρό
    -0.40
     murky
    -0.40
     jack
    -0.39
    sumi
    -0.39
    savevideo
    -0.39
     ويكيميديا
    -0.39
    POSITIVE LOGITS
    EndContext
    0.55
    VersionUID
    0.49
    ponses
    0.47
     varandra
    0.47
     äls
    0.46
     juntos
    0.44
     fidélité
    0.44
     setia
    0.43
    Together
    0.43
    spania
    0.42
    Act Density 0.002%

    No Known Activations