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

    Neuronpedia

    INDEX
    Explanations

    respective concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     улы
    0.33
    ژگی
    0.33
     რომლებიც
    0.33
     kDa
    0.32
    ccoli
    0.31
    োহণ
    0.31
     kiuj
    0.31
     मर्द
    0.31
     ফেলা
    0.31
     ragazzo
    0.30
    POSITIVE LOGITS
     respective
    0.44
    各自
    0.34
     jeweiligen
    0.34
    それぞれの
    0.33
     positions
    0.32
     respectivas
    0.32
    positions
    0.30
    respective
    0.30
     personas
    0.30
     tongues
    0.30
    Act Density 0.000%

    No Known Activations