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

    Neuronpedia

    INDEX
    Explanations

    development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    普段
    0.47
    writeHead
    0.46
    த்தனர்
    0.44
    टाला
    0.43
    ர்க்
    0.42
     antigos
    0.42
     члены
    0.41
    id
    0.41
     upstairs
    0.41
     newbies
    0.41
    POSITIVE LOGITS
     geliş
    0.51
    tevõ
    0.45
     desarrollo
    0.45
     ਵ
    0.44
     utveck
    0.44
     meer
    0.44
     розви
    0.43
     myös
    0.43
    thebetter
    0.43
     sviluppo
    0.42
    Act Density 0.005%

    No Known Activations