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

    Neuronpedia

    INDEX
    Explanations

    numeric values and date formats

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

    dates and slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.72
     zijne
    -0.67
     zoude
    -0.66
     mijne
    -0.66
     spørs
    -0.60
     betrek
    -0.60
     huden
    -0.59
     męski
    -0.58
     černá
    -0.58
     belangrij
    -0.57
    POSITIVE LOGITS
    /
    0.53
    Jereo
    0.49
    Сегодня
    0.47
     nakalista
    0.47
    @
    0.44
    {}/
    0.44
    /@
    0.43
     ПА
    0.43
     Seitz
    0.42
    ~/
    0.42
    Act Density 0.010%

    No Known Activations