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

    Neuronpedia

    INDEX
    Explanations

    visual display and layout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    för
    0.44
    城県
    0.44
    ovej
    0.43
     ۔
    0.43
    äär
    0.41
    iture
    0.40
    imą
    0.40
    ัติ
    0.40
    ocity
    0.40
    esters
    0.40
    POSITIVE LOGITS
    精灵
    0.40
     ayahuasca
    0.38
     chibi
    0.37
    ዠ
    0.37
     আক্রমণ
    0.37
     Luftwaffe
    0.36
     phenyl
    0.36
     Lactobacillus
    0.36
     benzodiazep
    0.36
     Naruto
    0.35
    Act Density 0.012%

    No Known Activations