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

    Neuronpedia

    INDEX
    Explanations

    latest news and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restraints
    0.56
     tannins
    0.52
     repudi
    0.48
     testator
    0.46
    它
    0.46
     wodurch
    0.45
     foreshadow
    0.44
    𝑏
    0.44
     testimonio
    0.44
     hes
    0.43
    POSITIVE LOGITS
    j
    0.69
    ニュース
    0.67
    news
    0.64
     news
    0.62
     noticias
    0.62
    updates
    0.62
    Новости
    0.61
    h
    0.61
    g
    0.60
     News
    0.59
    Act Density 0.150%

    No Known Activations