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

    Neuronpedia

    INDEX
    Explanations

    privacy, security, dignity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ప్రాంత
    0.47
     வேற
    0.47
    depends
    0.44
     وجہ
    0.44
    ដែលអាច
    0.44
    <0xAD>
    0.43
    varchar
    0.43
    categorie
    0.42
     depends
    0.42
    你怎么
    0.42
    POSITIVE LOGITS
     мар
    0.44
     घटनाएं
    0.44
    ک
    0.43
     kombin
    0.42
     lemb
    0.41
    }$.
    0.41
    Το
    0.41
     kindle
    0.41
     ک
    0.41
     empat
    0.41
    Act Density 0.001%

    No Known Activations