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

    Neuronpedia

    INDEX
    Explanations

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -done
    -0.06
    apache
    -0.06
    розум
    -0.06
     할인
    -0.06
    τώ
    -0.06
     similarly
    -0.06
    -two
    -0.06
    ‌هایی
    -0.05
    (tableView
    -0.05
    าจาก
    -0.05
    POSITIVE LOGITS
     pneumonia
    0.07
    arhus
    0.06
    穴
    0.06
     compulsory
    0.06
     inherited
    0.06
     HVAC
    0.06
    678
    0.06
     систему
    0.06
     coils
    0.06
    >();
↵
    0.06
    Act Density 0.003%

    No Known Activations