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

    Neuronpedia

    INDEX
    Explanations

    patterns in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ları
    0.50
    ുകൾ
    0.45
    泉
    0.44
    न
    0.43
    し
    0.43
    Marca
    0.43
     réellement
    0.42
    participant
    0.42
     soglas
    0.42
    Ｉ
    0.42
    POSITIVE LOGITS
     Oppen
    0.50
     Dirichlet
    0.45
     GHz
    0.44
     monies
    0.44
     innovations
    0.43
     Retail
    0.43
     GPT
    0.43
     ISR
    0.43
    ging
    0.42
     为
    0.42
    Act Density 0.001%

    No Known Activations