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

    Neuronpedia

    INDEX
    Explanations

    temporal indicators and phrases related to time

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

    time-related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erfolgreichen
    -0.33
     cepat
    -0.30
     start
    -0.29
     erfolgreiche
    -0.28
     quick
    -0.28
     remaining
    -0.28
     rápida
    -0.27
     prochaines
    -0.27
     veiks
    -0.27
    udahan
    -0.26
    POSITIVE LOGITS
    ésultats
    0.82
    UnsafeEnabled
    0.78
    expandindo
    0.77
    __(/*!
    0.76
    IndentedString
    0.75
    ſelves
    0.75
    нгред
    0.74
    RegistryLite
    0.73
    ſicht
    0.71
    ſelf
    0.70
    Act Density 0.051%

    No Known Activations