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

    Neuronpedia

    INDEX
    Explanations

    multilingual specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     מס
    0.44
     सीएस
    0.42
    REPORT
    0.42
     तहरी
    0.42
     vinculado
    0.42
    ➵
    0.42
     bağlant
    0.41
     டெ
    0.41
    簌
    0.41
     potencial
    0.40
    POSITIVE LOGITS
    сть
    0.41
    ться
    0.37
     hexa
    0.36
     môn
    0.36
     swallowing
    0.34
     thawing
    0.34
    之
    0.34
    ум
    0.34
    дена
    0.33
    ანი
    0.33
    Act Density 0.000%

    No Known Activations