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

    Neuronpedia

    INDEX
    Explanations

    exit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đủ
    -0.07
    отов
    -0.07
    pivot
    -0.07
     واست
    -0.07
    ようになりました
    -0.07
     competent
    -0.06
    虚拟
    -0.06
     ingestion
    -0.06
    ∋
    -0.06
    duğ
    -0.06
    POSITIVE LOGITS
     racial
    0.08
    }elseif
    0.07
    isha
    0.07
    iants
    0.07
    眼
    0.07
    уни
    0.07
    上班
    0.06
     maritime
    0.06
     마
    0.06
    ற
    0.06
    Act Density 0.003%

    No Known Activations