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

    Neuronpedia

    INDEX
    Explanations

    time displays and specific dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hearted
    1.98
    ्य
    1.90
    S
    1.73
    𝐧
    1.68
    𝗮
    1.67
    𝗹
    1.63
    checkBox
    1.62
    𝘯
    1.62
    ﻲ
    1.61
    𝗿
    1.61
    POSITIVE LOGITS
     aast
    1.50
    weekday
    1.49
     esist
    1.49
    т
    1.47
     potrz
    1.47
    মনসিংহ
    1.46
     će
    1.45
     Palash
    1.45
     actu
    1.43
     Rejected
    1.41
    Act Density 0.005%

    No Known Activations