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

    Neuronpedia

    INDEX
    Explanations

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inferiore
    0.45
    Ли
    0.45
    玼
    0.44
    aremos
    0.43
    ফটেন্যান্ট
    0.43
    ੱ
    0.43
     vois
    0.43
    িগ্ন
    0.42
    谈
    0.42
    elé
    0.42
    POSITIVE LOGITS
     Hinduism
    0.43
     prodigious
    0.42
     आत्महत्या
    0.40
     Hindu
    0.40
     spectacular
    0.40
     suicide
    0.40
     breathtaking
    0.40
     त्याचा
    0.39
     W
    0.39
     philosophy
    0.38
    Act Density 0.001%

    No Known Activations