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

    Neuronpedia

    INDEX
    Explanations

    options and relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lack
    0.62
    ரு
    0.60
    SUR
    0.59
    ায়ক
    0.57
     lacked
    0.55
     Lives
    0.54
     vac
    0.54
    中毒
    0.54
     blocking
    0.54
     walk
    0.54
    POSITIVE LOGITS
     Clément
    0.64
    ாட
    0.63
    ന്യൂ
    0.62
     영업
    0.61
    subprocess
    0.60
     ਸਮ
    0.60
    öglichkeiten
    0.60
     prawn
    0.59
    成交
    0.58
     முதல்வர்
    0.58
    Act Density 0.108%

    No Known Activations