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

    Neuronpedia

    INDEX
    Explanations

    name in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Raw
    0.41
     uncooked
    0.41
     pronta
    0.41
    ිය
    0.39
     materialistic
    0.38
    𝙷
    0.38
     newdata
    0.38
     mountainous
    0.38
     présenté
    0.38
    स्त्रा
    0.38
    POSITIVE LOGITS
    名称
    0.91
    名稱
    0.85
     name
    0.84
     naming
    0.82
     이름을
    0.80
    name
    0.78
     names
    0.77
     namn
    0.76
     имена
    0.74
     Namen
    0.73
    Act Density 0.443%

    No Known Activations